Abstract:Intelligent Transportation Systems (ITS) applications in public transportation have allowed for automated data collection, which is particularly useful for planning and operations. While technological advancement of ITS has so far been extensive, their usage for developing relevant planning and operational tools is rather limited. Research on planning and operations of public transportation systems has not widely investigated the potential of combining optimization models with data originating from ITS. Such a… Show more
“…Xiaolei et al [11] demonstrated a data-mining procedure using transit data for Beijing, China. Christina and Konstantinos [12] argued in favor of combining optimization models with data originating from information technology services (ITS). Rosario et al [13] reviewed the advancement of emergent technologies, and their implementations and applications with respect to smart power grids and cities.…”
Timely and efficient analysis of big data collected from various gateways installed in a smart city is an intractable problem and requires immediate priority. Given the stochastic and massive nature of big data, the existing literature often relies on artificial intelligence techniques based on information theory. As a new approach, this paper presents a knowledge extraction method based on an analysis of Seoul Metro's 'untraceable' ridership big data. Without identification information, the untraceable ridership data only shows the hourly accumulation of station entry and exit information. To reconstruct the missing information in the data set, this study proposes a fluid dynamics model and adopts a heuristic genetic algorithm based on optimization theory as the problem solver. The result of our model presents the distribution of the elapsed time defined on an hourly basis taken until a passenger returns to the station they departed from. To validate our model, we acquired subway ridership data with passengers' identification with permission from Seoul Metro. This paper presents two novel aspects of subway ridership, namely the dependency on departure time and the discrepancy between weekend and weekday traffic. Our analytical approach contributes to solving the problem of extracting hidden knowledge from big collection of data missing critical information, e.g., constantly and autonomously gathered data fragments from numerous gateways in smart cities. INDEX TERMS Inverse problem, genetic algorithm (GA), optimization, wave decomposition, harmony search algorithm, mass conservation law, data mining, outdoor duration time, Seoul metro subway ridership.
“…Xiaolei et al [11] demonstrated a data-mining procedure using transit data for Beijing, China. Christina and Konstantinos [12] argued in favor of combining optimization models with data originating from information technology services (ITS). Rosario et al [13] reviewed the advancement of emergent technologies, and their implementations and applications with respect to smart power grids and cities.…”
Timely and efficient analysis of big data collected from various gateways installed in a smart city is an intractable problem and requires immediate priority. Given the stochastic and massive nature of big data, the existing literature often relies on artificial intelligence techniques based on information theory. As a new approach, this paper presents a knowledge extraction method based on an analysis of Seoul Metro's 'untraceable' ridership big data. Without identification information, the untraceable ridership data only shows the hourly accumulation of station entry and exit information. To reconstruct the missing information in the data set, this study proposes a fluid dynamics model and adopts a heuristic genetic algorithm based on optimization theory as the problem solver. The result of our model presents the distribution of the elapsed time defined on an hourly basis taken until a passenger returns to the station they departed from. To validate our model, we acquired subway ridership data with passengers' identification with permission from Seoul Metro. This paper presents two novel aspects of subway ridership, namely the dependency on departure time and the discrepancy between weekend and weekday traffic. Our analytical approach contributes to solving the problem of extracting hidden knowledge from big collection of data missing critical information, e.g., constantly and autonomously gathered data fragments from numerous gateways in smart cities. INDEX TERMS Inverse problem, genetic algorithm (GA), optimization, wave decomposition, harmony search algorithm, mass conservation law, data mining, outdoor duration time, Seoul metro subway ridership.
“…Iliopoulou and Kepaptsoglou [8] have presented a detailed literature review of usage of ITS data from public transportation for planning and decision making. Especially from the tactical planning perspective, the availability of AVLS and ETM data helps improve the OD demand estimation and thereby timetable design.…”
Section: Literature Surveymentioning
confidence: 99%
“…1) is a challenge and needs to be addressed on a case-by-case basis. This issue is surveyed in detail under the data quality considerations topic of Iliopoulou and Kepaptsoglou [8].…”
Section: Lack Of Standardization Across Data Sources and Formatsmentioning
confidence: 99%
“…Appropriate enforcement of regulations by public transport authorities can make the operations more predictable and hence lead to the efficiency improvement, such as those implemented in developed countries. This issue is surveyed in detail under Operational planning topic of Iliopoulou and Kepaptsoglou [8] and treated as an optimization parameter in Yan et al [11].…”
Section: Insufficient Enforcement Of Regulationsmentioning
Urban bus transport is an important mode of public transportation in developing countries and accounts for the major share of daily commuter demand in growing cities. However, many of these systems are not optimized and suffer from delays, cancellations and overcrowding , leading to losses. In recent times, intelligent transport systems (ITS) have been deployed to improve the bus operations. However, the ITS deployed in developing nations have been limited to monitoring daily operations, largely due to their dynamic and unpredictive demand pattern. Bus transport operators need new ITS solutions for schedule optimization and fleet management to improve the efficiency and profitability. Simulation driven optimization of operational parameters is one of the methods to propose the advantages of integrating ITS solutions with the bus operations. The primary data utilized for analysis includes both the static and dynamic sources. The static data consists of route, schedule, vehicle and historical ticket information. Whereas the dynamic data includes GPS traces and Automatic Vehicle Location System (AVLS) information. The simulation consists of models of bus operations as well as the passenger ridership. Each of these are interdependent and directly impact the measurable performance indicators for the transport operators (for example, passenger load factor, departure headways, vehicle utilization and earnings). Therefore, the goal of the proposed simulator is to optimize these measurable key performance indicators (KPI) through their iterative schedule evaluation. In this paper, the methods used to model bus transportation are investigated and the impact on measurable performance indicators are evaluated. The simulator can not only be used to optimize the schedule, but also to evaluate passenger load and bus fleet utilization scenarios. In addition to evaluation of schedule for typical urban scenario, the conditions in developing countries and application difficulties are discussed. In summary, the results indicate that demand driven scheduling results in cost savings and efficiency improvement.
“…T HE combination of timetable information and Automatic Fare Collecting systems (AFC) is being used more broadly by researchers and practitioners to understand public transportation on the strategic, tactical and operational level [1], [2], [3]. This has lead to the identification of issues with the data used [1], [2], [3], [4], [5], [6], [7]. It has been shown that buses using AVL can have errors due to broken GPS units (hardware error), the bus deviating from the scheduled route (operational error) or busses not uploading data (data error) [5], which can lead to the travellers having the wrong alighting stop stored [4].…”
Smart card data from the Automatic Fare Collecting systems (AFC) and timetable information, such as Automatic Vehicle Location (AVL), are used in combination by practitioners and researchers to gain a deeper understanding of the public transit network. In some cases, AVL data are not available due to records being missing in the system. In such cases, people resort to the used schedule timetable such as General Transit Feed Specification (GTFS) to match smart card data to the transit network. Since delays or changes to the timetable are not contained in the scheduled timetable, it can result in wrong matches between the smart card data and the transit network. This paper shows how the uncertainty of arrival and departure times affects passengers to train assignments and proposes a method for estimating the missing arrival time of trains when the recorded timetable information is not available. The method uses the knowledge of how the tap-outs are distributed in a hierarchical, latent Bayesian model to predict the arrival times of trains. Evaluated on 15,136 train arrivals, the model can infer 70% of the arrivals times with an average error of 28 to 32 seconds depending on the station.
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.