Traffic flow breakdown prediction using feature reduction through Rough-Neuro fuzzy Networks

The prediction of the traffic behavior could help to make decision about the routing process, as well as enables gains on effectiveness and productivity on the physical distribution. This need motivated the search for technological improvements in the Routing performance in metropolitan areas. The purpose of this paper is to present computational evidences that Artificial Neural Network ANN could be use to predict the traffic behavior in a metropolitan area such So Paulo (around 16 million inhabitants). The proposed methodology involves the application of Rough-Fuzzy Sets to define inference morphology for insertion of the behavior of Dynamic Routing into a structured rule basis, without human expert aid. The dynamics of the traffic parameters are described through membership functions. Rough Sets Theory identifies the attributes that are important, and suggest Fuzzy relations to be inserted on a Rough Neuro Fuzzy Network (RNFN) type Multilayer Perceptron (MLP) and type Radial Basis Function (RBF), in order to get an optimal surface response. To measure the performance of the proposed RNFN, the responses of the unreduced rule basis are compared with the reduced rule one. The results show that by making use of the Feature Reduction through RNFN, it is possible to reduce the need for human expert in the construction of the Fuzzy inference mechanism in such flow process like traffic breakdown. © 2011 IEEE.

Turun seudun turvallisen ja kestävän liikkumisen suunnitelma

Turun seudun turvallisen ja kestävän liikkumisen suunnitelma on laadittu seudun kuntien ja Varsinais-Suomen ELY-keskuksen yhteistyönä. Suunnitelmassa on selvitetty liikenneturvallisuuden, liikkumisen, toimintaympäristön ja liikennejärjestelmän nykytilaa sekä kartoitettu liikenneturvallisuusongelmia erilaisten analyysien ja kyselyiden avulla. Nykytila-analyysin pohjalta on asetettu liikenneturvallisuustyön visio ja tavoitteet sekä määritetty toimenpide-ehdotukset. Tavoitteisiin pääsemistä tukevat liikenneympäristön parantamistoimenpiteiden ohjelma, liikkumisen ohjauksen toimintaohjelma sekä hallintokuntien liikenneturvallisuustyön toimenpiteistä kootut toimintasuunnitelmat. Onnettomuusanalyysin perusteella liikenneturvallisuuden tila oli Turun seudulla hieman koko Suomen keskiarvoa heikompi. Seudulla tapahtui vuosina 2001-2010 henkilövahinkoon johtaneita onnettomuuksia keskimäärin 132 / 100 000 asukasta, kun vastaava luku oli 126 koko maan osalta. Kuolemaan johtaneita onnettomuuksia tapahtui seudulla vähemmän, mutta loukkaantumiseen johtaneita onnettomuuksia koko maan keskiarvoa enemmän. Onnettomuuksissa kuoli tai loukkaantui koko maan keskiarvoa enemmän jalankulkijoita ja polkupyöräilijöitä. Lukumäärällisesti eniten onnettomuuksia tapahtui 18–19-vuotiaille, mutta henkilövahinkoon johtaneita onnettomuuksia tapahtui selvästi eniten 15–16-vuotiaille. Seudulla tapahtuneista liikenneonnettomuuksista aiheutui vuosittain keskimäärin 127,2 miljoonan euron kustannukset, josta kuntien osuus oli vuosittain noin 22,3 miljoonaa euroa. Asukkaille suunnatun kyselyn mukaan sekä työmatkat että lyhyet vapaa-ajan matkat tehtiin useimmiten henkilöautolla. Koululaisia pidettiin turvattomimpana tienkäyttäjäryhmänä, ja kävelyä sekä pyöräilyä turvattomimpina kulkutapoina. Välinpitämättömyyttä pidettiin merkittävimpänä syynä erilaisiin liikennerikkomuksiin ja tärkeimmäksi kehittämistarpeeksi nousi liikennekäyttäytyminen. Yhdyskuntarakenteen ja toimintaympäristön analyysin perusteella seudulla on hyvät edellytykset kestävien kulkumuotojen kuten joukkoliikenteen houkuttelevuuden lisäämiselle sekä kävelyn ja pyöräilyn verkoston kehittämiselle. Onnettomuusanalyysin ja valtakunnallisten tavoitteiden pohjalta Turun seudulle asetettiin liikenneturvallisuustyön tavoitteet. Tavoitelaskelman mukaan liikennekuolemien ja loukkaantuneiden määrä tulee puolittaa vuosien 2006-2010 keskiarvosta vuoteen 2020 mennessä. Tavoitteen mukaan liikenteessä kuolee enintään 6 (lähtötaso 12) ja loukkaantuu 236 (lähtötaso 471) vuonna 2020. Vaikutusarvion perusteella voidaan arvioida päästävän tavoitteeseen suunnitelmakauden aikana. Tavoitteiden saavuttaminen on kuitenkin haasteellista ja edellyttää tehokasta yhteistyötä eri tahojen välillä. Tavoitteeseen tulee pyrkiä laajaa keinovalikoimaa käyttäen. Suunnitelmatyön aikana aktivoitiin kuntien turvallisen ja kestävän liikkumisen ryhmät, joiden toiminnan tueksi laadittiin toimintasuunnitelmat sekä vuosikello työn eri vaiheista. Ryhmät vastaavat suunnitelman toteuttamisesta, toteutumisen seurannasta ja tarvittaessa päivittämisestä.

Yhdessä tuumin kohti turvallisempaa liikkumista : Loimaan seudun liikenneturvallisuussuunnitelma

Loimaan seudun liikenneturvallisuussuunnitelma on laadittu seudun kuntien ja Varsinais-Suomen ELY-keskuksen yhteistyönä. Liikenneturvallisuussuunnitelman tavoitteena on edistää kokonaisvaltaisella tavalla nykyistä vastuullisempaa ja turvallisuushakuisempaa liikkumista seudulla. Suunnitelmassa esitetyillä toimenpiteillä pyritään merkittävästi vähentämään seudulla tapahtuvien liikennekuolemien ja liikenteessä loukkaantuneiden määrää. Tavoitteena on myös edistää nykyistä kestävämpää liikkumista, jolla terveys- ja ympäristövaikutusten ohella on myönteinen vaikutus myös liikenneturvallisuuskehitykseen. Loimaan seudulla tapahtuu vuosittain keskimäärin viisi kuolemaan ja 70 loukkaantumiseen johtanutta onnettomuutta. Asukaslukuun suhteutettuna Loimaan seudulla tapahtuu selvästi enemmän henkilövahinko-onnettomuuksia kuin maakunnassa tai koko maassa keskimäärin. Myös liikenneonnettomuuksien vakavuusaste on maakunnan ja koko maan keskitasoa korkeampi. Kulkutavoittain tarkasteltuna korostuvat erityisesti henkilöauto-onnettomuudet. Liikennekuolemista peräti kolme neljäsosaa on tapahtunut autoilijoille. Ikäryhmittäin tarkasteltuna suurin onnettomuusriski on 15–24-vuotiailla, jotka muodostavat seudun liikenteen uhreista 39 prosenttia (ikäryhmän osuus seudun väestöstä on 11 prosenttia). Liikenneonnettomuuksista aiheutuu seudun kunnille vuosittain lähes kahdeksan miljoonan euron kustannukset – yli 200 euroa asukasta kohden. Nykytilan kuvausten pohjalta ja valtakunnalliset linjaukset huomioiden seudun liikenneturvallisuustyölle on asetettu pitkän aikavälin visio, määrälliset liikenneonnettomuuksien vähentämistavoitteet sekä lähivuosien toimintaa suuntaavat kärkitehtävät. Tavoitteiden mukaan seudun liikennekuolemien määrän tulee vähentyä nykyisestä viidestä hengestä1-2 henkeen vuoteen 2020 mennessä. Loukkaantumisten määrän tulee vähentyä nykyisestä 95 henkilöstä vähintään 71 henkilöön vuoteen 2020 mennessä (-25 %). Suunnitelmassa asetettujen tavoitteiden saavuttamiseen pyritään monipuolisen ja toimien vaikuttavuuden perusteella kohdennetun toimenpidejoukon keinoin sekä kehittämällä eri toimijoiden välistä yhteistyötä ja työnjakoa toimenpiteiden edistämisessä. Suunnitelmassa on esitetty 14 kärkitehtäväkokonaisuutta, joihin toiminta tulee vaikuttavuuden perusteella ensisijaisesti kohdistaa. Suunnitelman vaikutustenarvioinnin perusteella voidaan todeta, että keinot asetettujen tavoitteiden saavuttamiseksi ovat olemassa, mutta tavoitteisiin pääseminen edellyttää erittäin suuria panostuksia kaikilla liikenneturvallisuustyön osa-alueilla, ja erityisesti liikennekäyttäytymiseen ja yhteistyöhön kohdistuvien toimenpiteiden osalta. Liikennekuolemien puolittamisen tavoite nykytasosta vuoteen 2020 on tehtyjen tarkastelujen perusteella mahdollista. Myös loukkaantumisten määrän vähentäminen on saavutettavissa esitetyin toimenpitein.

Uso de álcool, comportamentos de risco no trânsito e habilidades sociais em universitários

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Knowledge-based spatiotemporal linear abstraction

We present a theoretical framework and a case study for reusing the same conceptual and computational methodology for both temporal abstraction and linear (unidimensional) space abstraction, in a domain (evaluation of traffic-control actions) significantly different from the one (clinical medicine) in which the method was originally used. The method, known as knowledge-based temporal abstraction, abstracts high-level concepts and patterns from time-stamped raw data using a formal theory of domain-specific temporal-abstraction knowledge. We applied this method, originally used to interpret time-oriented clinical data, to the domain of traffic control, in which the monitoring task requires linear pattern matching along both space and time. First, we reused the method for creation of unidimensional spatial abstractions over highways, given sensor measurements along each highway measured at the same time point. Second, we reused the method to create temporal abstractions of the traffic behavior, for the same space segments, but during consecutive time points. We defined the corresponding temporal-abstraction and spatial-abstraction domain-specific knowledge. Our results suggest that (1) the knowledge-based temporal-abstraction method is reusable over time and unidimensional space as well as over significantly different domains; (2) the method can be generalized into a knowledge-based linear-abstraction method, which solves tasks requiring abstraction of data along any linear distance measure; and (3) a spatiotemporal-abstraction method can be assembled from two copies of the generalized method and a spatial-decomposition mechanism, and is applicable to tasks requiring abstraction of time-oriented data into meaningful spatiotemporal patterns over a linear, decomposable space, such as traffic over a set of highways.

VISSIM Calibration for Urban Freeways, 2015

In urban areas, interchange spacing and the adequacy of design for weaving, merge, and diverge areas can significantly influence available capacity. Traffic microsimulation tools allow detailed analyses of these critical areas in complex locations that often yield results that differ from the generalized approach of the Highway Capacity Manual. In order to obtain valid results, various inputs should be calibrated to local conditions. This project investigated basic calibration factors for the simulation of traffic conditions within an urban freeway merge/diverge environment. By collecting and analyzing urban freeway traffic data from multiple sources, specific Iowa-based calibration factors for use in VISSIM were developed. In particular, a repeatable methodology for collecting standstill distance and headway/time gap data on urban freeways was applied to locations throughout the state of Iowa. This collection process relies on the manual processing of video for standstill distances and individual vehicle data from radar detectors to measure the headways/time gaps. By comparing the data collected from different locations, it was found that standstill distances vary by location and lead-follow vehicle types. Headways and time gaps were found to be consistent within the same driver population and across different driver populations when the conditions were similar. Both standstill distance and headway/time gap were found to follow fairly dispersed and skewed distributions. Therefore, it is recommended that microsimulation models be modified to include the option for standstill distance and headway/time gap to follow distributions as well as be set separately for different vehicle classes. In addition, for the driving behavior parameters that cannot be easily collected, a sensitivity analysis was conducted to examine the impact of these parameters on the capacity of the facility. The sensitivity analysis results can be used as a reference to manually adjust parameters to match the simulation results to the observed traffic conditions. A well-calibrated microsimulation model can enable a higher level of fidelity in modeling traffic behavior and serve to improve decision making in balancing need with investment.

Real-time analytics on large dynamic graphs

In today's fast-paced and interconnected digital world, the data generated by an increasing number of applications is being modeled as dynamic graphs. The graph structure encodes relationships among data items, while the structural changes to the graphs as well as the continuous stream of information produced by the entities in these graphs make them dynamic in nature. Examples include social networks where users post status updates, images, videos, etc.; phone call networks where nodes may send text messages or place phone calls; road traffic networks where the traffic behavior of the road segments changes constantly, and so on. There is a tremendous value in storing, managing, and analyzing such dynamic graphs and deriving meaningful insights in real-time. However, a majority of the work in graph analytics assumes a static setting, and there is a lack of systematic study of the various dynamic scenarios, the complexity they impose on the analysis tasks, and the challenges in building efficient systems that can support such tasks at a large scale. In this dissertation, I design a unified streaming graph data management framework, and develop prototype systems to support increasingly complex tasks on dynamic graphs. In the first part, I focus on the management and querying of distributed graph data. I develop a hybrid replication policy that monitors the read-write frequencies of the nodes to decide dynamically what data to replicate, and whether to do eager or lazy replication in order to minimize network communication and support low-latency querying. In the second part, I study parallel execution of continuous neighborhood-driven aggregates, where each node aggregates the information generated in its neighborhoods. I build my system around the notion of an aggregation overlay graph, a pre-compiled data structure that enables sharing of partial aggregates across different queries, and also allows partial pre-computation of the aggregates to minimize the query latencies and increase throughput. Finally, I extend the framework to support continuous detection and analysis of activity-based subgraphs, where subgraphs could be specified using both graph structure as well as activity conditions on the nodes. The query specification tasks in my system are expressed using a set of active structural primitives, which allows the query evaluator to use a set of novel optimization techniques, thereby achieving high throughput. Overall, in this dissertation, I define and investigate a set of novel tasks on dynamic graphs, design scalable optimization techniques, build prototype systems, and show the effectiveness of the proposed techniques through extensive evaluation using large-scale real and synthetic datasets.

Towards effective control of P2P traffic aggregates in network infrastructures

Nowadays, many P2P applications proliferate in the Internet. The attractiveness of many of these systems relies on the collaborative approach used to exchange large resources without the dependence and associated constraints of centralized approaches where a single server is responsible to handle all the requests from the clients. As consequence, some P2P systems are also interesting and cost-effective approaches to be adopted by content-providers and other Internet players. However, there are several coexistence problems between P2P applications and In- ternet Service Providers (ISPs) due to the unforeseeable behavior of P2P traffic aggregates in ISP infrastructures. In this context, this work proposes a collaborative P2P/ISP system able to underpin the development of novel Traffic Engi- neering (TE) mechanisms contributing for a better coexistence between P2P applications and ISPs. Using the devised system, two TE methods are described being able to estimate and control the impact of P2P traffic aggregates on the ISP network links. One of the TE methods allows that ISP administrators are able to foresee the expected impact that a given P2P swarm will have in the underlying network infrastructure. The other TE method enables the definition of ISP friendly P2P topologies, where specific network links are protected from P2P traffic. As result, the proposed system and associated mechanisms will contribute for improved ISP resource management tasks and to foster the deployment of innovative ISP-friendly systems.

Examining Driver Behavior in Response to Work Zone Interventions: A Driving Simulator Study, 2010

Construction zones pose a significant threat to both workers and drivers causing numerous injuries and deaths each year. Innovations in work zone safety could reduce these numbers. However, implementing work zone interventions before they are validated can undermine rather than enhance safety. The objective of this research is to demonstrate how driving simulators can be used to evaluate the effect of various work zone interventions on driver performance.

Drivers' Behavior at Railroad Grade Crossings: Before and After Safety Campaign, HR-335, 1992

In April 1991 the Iowa Department of Transportation, the CNW Transportation Company, the SOO Line, and local agencies and business in the Mason City/Clear Lake area initiated an Operation Lifesaver program to attempt to increase public awareness of safety issues and safe behavior at railroad-highway grade crossings. This document reports an initial study of data on traffic characteristics at a selected set of grade crossings in Cerro Gordo County taken before and after the safety program. Twenty-two crossings were studied. The 13 crossings at which collisions were reported for the five years prior to the study were included in the sample of sites. Two field observations were made at each study crossing before the Operation Lifesaver campaign was in full swing, and two observations were made after the conclusion of the main effort of the campaign. The summary of each data set is contained in a companion volume. The research shows that Operation Lifesaver altered drivers' behavior in the following ways: (1) reduced approach speeds and crossing speeds at crossings with low speed limits, (2) reduced the percent of drivers approaching the crossing at speeds in excess of the posted speed limit, and (3) increased alertness of drivers to railroad crossing hazards as evidenced by more drivers looking for a clear track. Thus, Operation Lifesaver enhanced safety in street and highway traffic operations in the vicinity of railroad-highway grade crossings.

Behavior of Carbonate Rocks as Concrete Aggregates, HR-15, 1962

The problem of determining the suitability of carbonate rocks as concrete aggregates is extremely complex and calls for more new data than has been available or obtainable from usual methods. Since 1955 the approach which has served as a primary basis for the project has been to gather as much new information as possible to apply to the problem. New information obtained by new and different techniques provides better understanding. This approach was decided on since, in all prior studies, a standard petrographic and petrologic approach correlated in many instances with standard engineering tests did not provide the answer in Iowa or elsewhere. One can theorize that concrete fails (excluding external causes such as traffic, foundation failure, etc.) because of stresses of internal origin. The stresses can be of a physical nature, such as frost action, or result from chemical activity such as the alkali aggregate reaction. If, as service records show, the aggregate is considered the cause of distress in concrete, it will without doubt be the manner in which an aggregate can create or contribute to stress of internal origin by physical or chemical means. Therefore the main emphasis was placed on studying physical and chemical properties of aggregates as well as the behavior of carbonate rocks in concrete environments. Although standard geologic and engineering methods were also utilized, the approach adopted required considerable effort in devising new techniques and methods. This report is intended to be a detailed summary of the research performed. Whenever possible, the work accomplished will be summarized and all pertinent data will be included. For further details, reference to the various theses and publications transmitted with this report or at previous times will be made wherever possible.

Service Correlation of the Traffic Simulator, HR-100, 1967

A study was undertaken by the Bituminous Research Laboratory of the Engineering Research Institute at Iowa State University, under the sponsorship of the Iowa Highway Research Board, project HR 100, to ascertain the effects of a number of characteristics and properties of asphaltic concrete mixes upon the service behavior of the mixes as evaluated by the Traffic Simulator and by field observations. The study included: Investigations of the relations, of gradation, fraction and resistance to wear of aggregates; of stability, cohesion, per cent voids and asphalt content: of a number of laboratory and field mixes to service behavior as indicated by the Traffic Simulator under various test conditions. Based upon the results of the tests and the relationships noted, tentative criteria for the Traffic Simulator test were devised, subject to verification by observations and measurements of field service behavior of the mixes.

Modeling Merging Behavior at Lane Drops, InTrans Projects 13-466 and 06-277, 2015

In work-zone configurations where lane drops are present, merging of traffic at the taper presents an operational concern. In addition, as flow through the work zone is reduced, the relative traffic safety of the work zone is also reduced. Improving work-zone flow-through merge points depends on the behavior of individual drivers. By better understanding driver behavior, traffic control plans, work zone policies, and countermeasures can be better targeted to reinforce desirable lane closure merging behavior, leading to both improved safety and work-zone capacity. The researchers collected data for two work-zone scenarios that included lane drops with one scenario on the Interstate and the other on an urban arterial roadway. The researchers then modeled and calibrated these scenarios in VISSIM using real-world speeds, travel times, queue lengths, and merging behaviors (percentage of vehicles merging upstream and near the merge point). Once built and calibrated, the researchers modeled strategies for various countermeasures in the two work zones. The models were then used to test and evaluate how various merging strategies affect safety and operations at the merge areas in these two work zones.

Wind Loads on Dynamic Message Cabinets and Behavior of Supporting Trusses, TR-612, 2013

Large Dynamic Message Signs (DMSs) have been increasingly used on freeways, expressways and major arterials to better manage the traffic flow by providing accurate and timely information to drivers. Overhead truss structures are typically employed to support those DMSs allowing them to provide wider display to more lanes. In recent years, there is increasing evidence that the truss structures supporting these large and heavy signs are subjected to much more complex loadings than are typically accounted for in the codified design procedures. Consequently, some of these structures have required frequent inspections, retrofitting, and even premature replacement. Two manufacturing processes are primarily utilized on truss structures - welding and bolting. Recently, cracks at welding toes were reported for the structures employed in some states. Extremely large loads (e.g., due to high winds) could cause brittle fractures, and cyclic vibration (e.g., due to diurnal variation in temperature or due to oscillations in the wind force induced by vortex shedding behind the DMS) may lead to fatigue damage, as these are two major failures for the metallic material. Wind and strain resulting from temperature changes are the main loads that affect the structures during their lifetime. The American Association of State Highway and Transportation Officials (AASHTO) Specification defines the limit loads in dead load, wind load, ice load, and fatigue design for natural wind gust and truck-induced gust. The objectives of this study are to investigate wind and thermal effects in the bridge type overhead DMS truss structures and improve the current design specifications (e.g., for thermal design). In order to accomplish the objective, it is necessary to study structural behavior and detailed strain-stress of the truss structures caused by wind load on the DMS cabinet and thermal load on the truss supporting the DMS cabinet. The study is divided into two parts. The Computational Fluid Dynamics (CFD) component and part of the structural analysis component of the study were conducted at the University of Iowa while the field study and related structural analysis computations were conducted at the Iowa State University. The CFD simulations were used to determine the air-induced forces (wind loads) on the DMS cabinets and the finite element analysis was used to determine the response of the supporting trusses to these pressure forces. The field observation portion consisted of short-term monitoring of several DMS Cabinet/Trusses and long-term monitoring of one DMS Cabinet/Truss. The short-term monitoring was a single (or two) day event in which several message sign panel/trusses were tested. The long-term monitoring field study extended over several months. Analysis of the data focused on trying to identify important behaviors under both ambient and truck induced winds and the effect of daily temperature changes. Results of the CFD investigation, field experiments and structural analysis of the wind induced forces on the DMS cabinets and their effect on the supporting trusses showed that the passage of trucks cannot be responsible for the problems observed to develop at trusses supporting DMS cabinets. Rather the data pointed toward the important effect of the thermal load induced by cyclic (diurnal) variations of the temperature. Thermal influence is not discussed in the specification, either in limit load or fatigue design. Although the frequency of the thermal load is low, results showed that when temperature range is large the restress range would be significant to the structure, especially near welding areas where stress concentrations may occur. Moreover stress amplitude and range are the primary parameters for brittle fracture and fatigue life estimation. Long-term field monitoring of one of the overhead truss structures in Iowa was used as the research baseline to estimate the effects of diurnal temperature changes to fatigue damage. The evaluation of the collected data is an important approach for understanding the structural behavior and for the advancement of future code provisions. Finite element modeling was developed to estimate the strain and stress magnitudes, which were compared with the field monitoring data. Fatigue life of the truss structures was also estimated based on AASHTO specifications and the numerical modeling. The main conclusion of the study is that thermal induced fatigue damage of the truss structures supporting DMS cabinets is likely a significant contributing cause for the cracks observed to develop at such structures. Other probable causes for fatigue damage not investigated in this study are the cyclic oscillations of the total wind load associated with the vortex shedding behind the DMS cabinet at high wind conditions and fabrication tolerances and induced stresses due to fitting of tube to tube connections.