Young-Ji Byon

Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction

Prediction of short-term traffic flow has become one of the major research fields in intelligent transportation systems. Accurately estimated traffic flow forecasts are important for operating effective and proactive traffic management systems in the context of dynamic traffic assignment. For predicting short-term traffic flows, recent traffic information is clearly a more significant indicator of the near-future traffic flow. In other words, the relative significance depending on the time difference between traffic flow data should be considered. Although there have been several research works for short-term traffic flow predictions, they are offline methods. This paper presents a novel prediction model, called online learning weighted support-vector regression (OLWSVR), for short-term traffic flow predictions. The OLWSVR model is compared with several well-known prediction models, including artificial neural network models, locally weighted regression, conventional support-vector regression, and online learning support-vector regression. The results show that the performance of the proposed model is superior to that of existing models.

Travel Time Collection and Traffic Monitoring Via GPS Technologies

Recently, GPS (Global Positioning System) technologies have been increasingly used in various applications of transportation planning and operations. When combined with GIS (geographic information systems), GPS data can be matched with spatial map features such as highways and roads for monitoring traffic conditions on those links. As one such application, GISTT (GPS-GIS integrated system for travel time surveys) was developed. GISTT collects and analyses traffic conditions of links by monitoring speed of probe vehicle(s) and then estimates travel time data both in static and dynamic modes. The static mode refers to the case of offline processing of GPS data from previously dispatched GPS-equipped vehicles to specified road links. The dynamic mode refers to the real time monitoring of speed on the links using a GPS-wireless Internet-equipped probe vehicle. GISTT is tested in various field tests and the results are found to be promising. Furthermore, the GISTT is to be extended by incorporating more complex dynamic algorithms to provide reliable real time traffic conditions. This paper sets a framework of the extended GISTT that contains algorithm to monitor traffic conditions by processing massive data from multiple GPS probes or GPS-enabled-cell-phones in real time. The algorithm involves identifying the traveling mode based on patterns found in relatively short time frame

Real-Time Transportation Mode Detection Using Smartphones and Artificial Neural Networks: Performance Comparisons Between Smartphones and Conventional Global Positioning System Sensors

Traditionally, traffic monitoring requires data from traffic cameras, loop detectors, or probe vehicles that are usually operated by dedicated employees. In efforts to reduce the capital and operational costs associated with traffic monitoring, departments of transportation have explored the feasibility of using global positioning system (GPS) data loggers on their probe vehicles that are postprocessed for analyzing the traffic patterns on desired routes. Furthermore, most cell phones are equipped with embedded assisted-GPS (AGPS) chips, and if the mode of transportation the phone is in can be anonymously identified, the phones can be treated as if they are probe vehicles that are voluntarily hovering throughout the city, at minimal additional costs. Emerging cell phones known as “smartphones” are equipped with additional sensors including an accelerometer and magnetometer. The accelerometer can directly measure the acceleration values, as opposed to having acceleration values derived from speed values in conventional GPS sensors. The magnetometer can measure mode-specific electromagnetic levels. Smartphones are subscribed with roadside Internet data plans that can provide an essential platform for real-time traffic monitoring. In this article, neural network-based artificial intelligence is used to identify the mode of transportation by detecting the patterns of distinct physical profile of each mode that consists of speed, acceleration, number of satellites in view, and electromagnetic levels. Results show that newly available values in smartphones improve the mode detection rates when compared with using conventional GPS data loggers. When smartphones are in known orientations, they can provide three-dimensional (3-D) acceleration values that can further improve mode detection accuracies.

TrafficPulse: a mobile GISystem for transportation

Today municipalities around the world spend millions of dollars to understand the dynamics of their transportation infrastructure. Traditional approaches for traffic data collection rely on a fixed sensor infrastructure (e.g., inductive loop detectors), and because these sensors are expensive to deploy and maintain, the traffic data coverage is limited to main highways and major intersections. This limited information hinders municipalities to achieve efficient traffic management and control. To address this problem, we develop TrafficPulse, a mobile GISystem platform for transportation applications. For the client front-end, we develop the TrafficPulse mobile application that collects traffic data by integrating participatory sensing, opportunistic sensing, and offline data collection module. For the server back-end, we develop Geopot cloud, a cloud-based geo-location data service for mobile applications. In order to demonstrate the potential benefit of this system, we also develop a carpooling recommendation system to analyze user-shared content and provide a recommendation service to TrafficPulse users. In this paper, we describe our system architecture and experiences, allowing our paper to be used as a reference for other developers who want to develop their own transportation applications.

Improvement of Search Strategy With K-Nearest Neighbors Approach for Traffic State Prediction

Having access to the future traffic state information is crucial in maintaining successful intelligent transportation systems (ITS). However, predicting the future traffic state is a challenging research subject involving prediction reliability issues. Predictive performance measures, including the accuracy, efficiency, and stability, are generally considered as the most important priorities in the evaluation of prediction modules. Researchers have developed various K-nearest-neighbors-based searching algorithms that find the future state from the historical traffic patterns. Interestingly, there has not been sufficient effort made for improving the performance. For the emerging big data era, incorporating an efficient search strategy has become increasingly important since the applicability of the prediction module in ITS heavily relies on the efficiency of the searching method used. This paper develops a novel sequential search strategy for traffic state predictions. The proposed sequential strategy is found to be outperforming the conventional single-level search approach in terms of prediction measures, which are prediction accuracy, efficiency, and stability. Compared with the conventional approach, the proposed sequential method yields significantly more accurate results via internal hierarchical improvements across sublevels while maintaining excellent efficiency and stability.

How to protect ADS-B: Confidentiality framework for future air traffic communication

Automatic Dependent Surveillance-Broadcast (ADSB) is one of the crucial technologies for future “e-Enabled” aircrafts. Basically, ADS-B uses avionics in the e-Enabled aircrafts to broadcast essential flight data such as the aircraft call sign, altitude, heading, and other extra positioning information. On one hand ADS-B brings significant benefits to the aviation industry, but on the other hand it could pose some security concern as channels between ground controllers and aircrafts for ADS-B communications are not secured and the ADS-B messages could be captured by random individuals who might own ADS-B receivers. For certain situations, those ADS-B data can be very critical, especially when communications occur among military and mission-critical civil airplanes. These communications need to be protected from any interruption and eavesdropping. The challenge here is to construct an encryption scheme fast enough for very frequent encryption and flexible enough for effective key management. To address these issues, we propose a Staged Identity Based Encryption (SIBE) scheme, which is an extended version of hybrid Identity-Based Encryption. Based on the the proposed SIBE scheme, we introduce a new confidentiality framework for future e-Enabled aircrafts with ADS-B capability.

Feasibility analysis of transportation applications based on APIs of social network services

With increasing ownership of smartphones and membership of various social network services (SNS), new types of Advanced Traveler Information Systems (ATIS) has become available to travelers. The smartphone enables mobile users to input and access real-time information while SNSs provide voluntarily collected personal information among networks of friends. Internet of Things (IoT) philosophy can be applied for connecting smartphone users for various transportation applications. This paper develops Facebook-based carpooling, and proposes Twitter-based traffic monitoring and Flickr-based incident reporting applications. The SNS services provide application programming interfaces (APIs) that allow external users to access their databases. The APIs provide a basis for the development of transportation applications for each service. Facebook can allow a group of friends to share a ride based on their attributes which are available in their personal information sections. Twitter can be used for sharing traffic conditions on the roads. Flickr can be customized as a geo-tagged collision reporting tool with real-time close-up photos of traffic collisions. It is found that available APIs are useful for implementing SNS-based transportation applications. It is also found that search times for carpooling partners vary with multiple factors: time-of-day, number of potential partners, and desired tolerance levels for location and time.

How to Protect ADS-B: Confidentiality Framework and Efficient Realization Based on Staged Identity-Based Encryption

Automatic Dependent Surveillance-Broadcast (ADS-B) is one of the key technologies for future “e-Enabled” aircrafts. ADS-B uses avionics in the e-Enabled aircrafts to broadcast essential flight data such as call sign, altitude, heading, and other extra positioning information. On the one hand, ADS-B brings significant benefits to the aviation industry, but, on the other hand, it could pose security concerns as channels between ground controllers and aircrafts for the ADS-B communication are not secured, and ADS-B messages could be captured by random individuals who own ADS-B receivers. In certain situations, ADS-B messages contain sensitive information, particularly when communications occur among mission-critical civil airplanes. These messages need to be protected from any interruption and eavesdropping. The challenge here is to construct an encryption scheme that is fast enough for very frequent encryption and that is flexible enough for effective key management. In this paper, we propose a Staged Identity-Based Encryption (SIBE) scheme, which modifies Boneh and Franklins original IBE scheme to address those challenges, that is, to construct an efficient and functional encryption scheme for ADS-B system. Based on the proposed SIBE scheme, we provide a confidentiality framework for future e-Enabled aircraft with ADS-B capability.

Incorporating Scenic View, Slope, and Crime Rate into Route Choices: Emphasis on Three-Dimensional Geographic Information Systems with Digital Elevation Models and Crime Rate Geospatial Data

With Global Positioning System (GPS) devices, drivers are now more confident in exploring routes out of the ordinary. More portable forms of commercial GPS navigators (GPS-embedded cell phones, MP3 players, and watches) are also available for pedestrians and bicyclists. Most route guidance applications minimize travel distance and time, which are important factors, but are not the only navigational criteria of interest to users, especially in urban and city environments. With the aid of advanced features of geographic information systems (GISs), new geospatial factors such as the three-dimensional (3-D) nature of the roads and crime rates can be included in the route guidance for broader applications. For instance, 3-D GISs can generate information on visible scenery along a given route (for tourists) or the slopes of the consecutive road segments (for pedestrians and bicyclists). In addition, pedestrians and bicyclists can opt to avoid high-crime areas. In the future, this concept of incorporating new geospatial information can be extended, for example, for computing low-elevation areas that are susceptible to flooding and hilly regions with heavy traffic. This paper presents methods of incorporating 3-D features of the roads and geospatial crime rate information for route guidance purposes. It is found that the 3-D nature of the roads and crime rate–related information can result in considerably different route choices.

Enhancing healthcare accessibility measurements using GIS: A case study in Seoul, Korea

With recent aging demographic trends, the needs for enhancing geo-spatial analysis capabilities and monitoring the status of accessibilities of its citizens with healthcare services have increased. The accessibility to healthcare is determined not only by geographic distances to service locations, but also includes travel time, available modes of transportation, and departure time. Having access to the latest and accurate information regarding the healthcare accessibility allows the municipal government to plan for improvements, including expansion of healthcare infrastructure, effective labor distribution, alternative healthcare options for the regions with low accessibilities, and redesigning the public transportation routes and schedules. This paper proposes a new method named, Seoul Enhanced 2-Step Floating Catchment Area (SE2SFCA), which is customized for the city of Seoul, where population density is higher and the average distance between healthcare-service locations tends to be shorter than the typical North American or European cities. The proposed method of SE2SFCA is found to be realistic and effective in determining the weak accessibility regions. It resolves the over-estimation issues of the past, arising from the assignment of high healthcare accessibility for the regions with large hospitals and high density of population and hospitals.