Academy of Strategic Management Journal (Print ISSN: 1544-1458; Online ISSN: 1939-6104)

Research Article: 2021 Vol: 20 Issue: 2

Management of Artificial Intelligence Traffic Systems in Smart Cities

Jamal M. Assbeihat, Al-Balqa Applied University

Nosheen Rafi, National College of Business Administration and Economics

Abstract

Purpose: The crop up of technologies has emerged in the direction of connected vehicle-infrastructure-pedestrian environment. It became convenient and have low cost to accumulate, stock, utilize, and disposal of data which is taken from different sources. The purpose of research paper is to develop the smart cities and traffic intelligence system by using Artificial Intelligence (AI) techniques and tricks in management of smart cities traffic networks. Methods: The data assembly of this paper explaining and mentioning review of the present vogue in intelligence of transportation. Findings: the findings from research of connected environment information elaborates Smart Traffic Mobility Management and finally the finding helps to plan activities for future ITS and smart cities. Value: the findings of the presented research will assist the administration of smart cities in analyzing public attitudes and perceptions from cyber sources, modelling of CSP Traffic Networks and flow models under connected.

Keywords

Traffic Intelligence, Artificial Intelligence, Global Positioning System.

Introduction

Issues that are explain in term of analysis and comprehension are mostly reserved by domain-dependent data origin. Towards a connected Vehicle-Infrastructure-Pedestrian (VIP) environment, recent arise in technologies and larger amount of data make it convenient and low cost to accommodate, store, analyze, utilize, and disperse multi-source information. System become more and more adaptable with the help of VIP environment so that system performance improved by implementing distinct-time arrangement and control measures (Henry, 2007). Vehicles, infrastructure, and pedestrians are able to exchange data and information through different connected environment, either through an associated concordat or a concentrate environment through 4G or much amazing networking such as tele-communication (VIP environment). For the urban environment these above-mentioned techniques are considered outstanding potentially innovative technologies. The interconnection, alternation as well as modification about data able to establish vehicle-to-vehicle, pedestrian to framework, vehicle to framework, or vehicle to pedestrian (Soriguera, 2011). Benefits that are given from connected environment and understanding of its unique properties and characteristics, it is easiest way to acknowledge the present intelligent transportation systems that modify to task load with the attached environment. Objective of this paper is to: (1) Review current progress of smart cities in Intelligent Transportation Systems (ITSs) and (2) Proffer insight on the establishment of connected VIP Eco-system into require organization and institutes. The data assembly of this paper arrange in such a way that the next section explaining and mentioning review of the present vogue in transportation organization of intelligence. Smart cities and relevant data of Artificial Intelligence (AI) techniques and tricks discussed in Section 3. Connected environment information elaborate within Section 4. Finally, Section 5 briefly explaining information about smart cities and ITSs (Nordback, 2016).

Trends in Intelligent Transportation Systems

There are several trends through which different can be operated and managed. These transportation systems yield many severe issues such as congestion, accidents, and air pollution as a consequence of the abrupt and sudden increase in different movement demands, freight, including traffic of vehicles, local transportation as well as pedestrian traffic (Michalopoulos, 1991). Thus, to tackle out all these issues, a broad range of systems can be integrated and for this purpose and information technology based smart traffic networks have been developed. The sensing, fruitful communication, data and information disposal, and traffic control are main purposes. These traffic networks are managed by these three functions: data gathers, data inspection, and data transmission (Fathy, 1998).

The components of data accumulator collect allover detectable material of details through the travelling station in road network of traffic. This is collected for a specific point, for a particular road section travelling time, a transit line through how many passengers bordering. The vehicles availability based on the induced flow in the loop can detect by using inductive loop detectors with passing vehicles (Chang, 2004). The presence of vehicles depends upon pressure variation in the tube that can be detected utilization of different and pneumatic tubes. If this method us analyzed using budgeting analysis then it proves to be costly especially in the areas where traffic is merged and it will also be difficult to manage the traffic while using multiple roads.

The other main managing traffic system is the utilization sensing technology on the roads. The sensing and imaging technology becoming very advance technologies and these can collect data using the scanning video cameras and Radio-Frequency Identification (RFID) (Li, 2013). To collect proper traffic data video cameras are designed at different stations in the system of network (Vanajakshi, 2009). Proper photography design software’s are used to for analyses purpose of traffic videos (e.g. Auto scope) so that data and information can determine such as traffic motion per minute, speed, which types of vehicles are using etc. One of the crucial areas of searching is Automatic license plate recognition explain in this context, recognition and similarities of authorized plates make us able to appropriate further data such as exact selection of paths and motion times (Dihua Sun, 2007). Second term explaining that the station which accept countless payment, radio-frequency detection data usually used there such as Auto toll and Octopus unit present in Hong Kong specially using cargo transportation. Various traffic-relevant information, such as track selection or travel time and selections, can be obtained from the matching of unique RFID method (Ashish Bhaskar, 2013).

Increasing penetration of for the detection of traffic situations or even travel situation smartphones and amazing communicating techniques, media access control usually regarded as the MACs addresses through Bluetooth, global positioning system and WiFi parts cell details are efficiently provided just because increasing penetration of these above terms (Antonin, 2014). If above listed data sources compared, at the level of the individual these unique kinds of data are more convenient, as such type of technology devices that are usually personalized, and consistence on tracking can be provided (e.g., GPS and cell data). Mostly elaborated and/or act-relevant detection able to gather with the help of these characteristics (Caceres, 2007).

ITSs have purpose to provide us with different data and arrangement/control data by data analysis components and these are done by using traffic data collection come out of these mentioned origins such as the sensors based on inductive loops and global positioning systems. Automatically defined and accurate models, such as equilibrium establishment in traffic models, flow models and for uniqueness of various models have been implemented to elaborate traffic station situations and essential responses may be provided, traditionally (Calabrese, 2013). Comparing power and the requirement for extra detailed consequences recently improved which have guide to the establishment of micro-simulation as well as in data analysis components which are agent-based models. As new sources of data/information appear then improve the concurrency and data of evaluations these models become a part of efficient use of the new data (Yang, 2004).

The gathered information to operation theaters for the purpose of analysis and disposal information, components of ITSs help communicate center play important role for the data/information transmission and/or appropriate alignment to infrastructures and travelers (Zhong, 2011). Collected data from transmission have evolved various methods from different wires to station of wireless networks of optical fibers, for instance Wifi 3G/4G, through cloud stage. Strategies of disposal data and control/management involves various method from conventional broadcasting signals of transportation vehicles of radio to mobile applications, alternate message polarity and in vehicle data by getting benefits of authentic communication technologies. ITSs can be classified into one of two categories with these basic components that depends upon their features (Zhong, 2011). Each one is presented below with description (Zhong, 2013).

Advanced Traveler Information Systems – ATISs work in favor of travelers that able to take travel decisions. These decisions are commonly the choice of mode term, route selection, and choice of departure time. These are taken with the help of different types of data. The data manipulated for this research is travel time, waiting time, area available for parking. Travel time prediction/observance and guidance of route systems (Zhong, 2013) are the utmost usual studied domain of the various implementations they are able to leave impacts on travelers' choices clearly, especially path choice (Li, 2004). Route guidance information as well as travel time available may be in a more appropriate and rational-time way with the uniqueness of the data-accommodation techniques and with communication technologies as mentioned above in text. The real-time data is also available to travelers with the more and more origin of data. The data available for this mode of work is the GPS data, mobile phone data. The practical assumptions of this data are the estimation of road-condition can be done by using photages from drivers picked from the smartphone applications that are based on the software implications. This is automatically that used to measure current required path side parking in distinct era (Liu, 2009). Prediction of bus arrival time is another example and this information travels by bus passengers via variable signals of mobile phone across various call towers (Kitamura, 2000).

On the other hand, the other important parameter is the Advanced Management Systems. This have purpose to arrange various infrastructures and operators under different situations within the transportation system. This mechanism will only to conform and increase the output and protection of transportation system. Such control/arrangement methods in the literature are implement to transit services, freeways, arterials, transports and incident/emergency situations (Yin, 2014). The data originated from these facts is enough to improve data resolution, and validate information dissemination method. For example, in real-time based bus location information Fu and Yang offered bus-caring boundary strategies to bus front way at fixed points. Only in simulation experiments, these data researchers have validated their own models and gives good insight into unique origin of information that could be utilized in transit management.

Management of Smart Cities Traffic Networks

The smart cities are cities having strong telecommunication networks. These telecommunication systems are utilized for the control of the traffic of different transportation systems. The different transportation-related issues are solved by the ITSs that describe in last section having purpose to come out with the solution and improve the efficiency to great extent of system of transportation. Thus, ITSs included the classification of smart motion within smart city framework and in recent ten years ITSs gain concerns about it (Siripirote, 2015). There is not yet agreement express the constituent of smart cities and these are expressed in diverse term. One example is of Hall give clue that a smart city able to bound its constituents mention as tracks, buildings, etc. up to great optimization of its assists, plan fend off preservation stunts, and controlling security, however enough amenity to its city fellow. Lombardi et al, a second side, offered the modern crowd that utilizing informative data and modern techniques (ICT) of communication on mankind funds, relational and social funds, and system problems. This description based on backbench of contributor and the concentration is on the administration. For a moment, efficiency of living to be the utmost goal of a smart municipal and it is improving as academia considers, however contributor in a self-organization might opt for maximum yield and it is the top most aim. Regardless of this assortment of elaboration by using latest electronic/digital technologies such as ICT, inserting ICT or different electronic hardware into smart cities infrastructure, and making efficient contributors’curiosity in various domains of cycle and are three usual terminologies or orientation of the smart municipal (Alena, 2007).

Smart municipal able to classify into six various constituents with the help of concerning features: smart administration, smart resources, smart social funds, smart eco system, smart life style, and smart motion. Smart administration purposes to utilize ICTs to increment the efficiency as well as transport benefits of public stations systems in alignment of local human economics, and to uplift people enrollment in risk taking (Athena, 2015). Latest municipal has the aim to give opportunities of employment of ICT as well as related tricks which is to give benefits of yield in the assembly of cycle and to make it more and more efficient and secure online business for the forward step of e-commerce. Unique municipal funds having goal to make more and more efficient the literacy standard and strong youth contribution of citizens via the provision plenty of knowledge surety through the other parts of the smart society. The Aim is to gather personal concepts and behavior, as required information are best information of any organization may provide (Shao, 2017). Main purpose of a modern eco system is to reduce entropy as well as tackle out other eco system problems within require time that improving residential sustainability via utilization of modern technologies. Smart Living attain to improve efficiency of life such as protection, housing efficiency, etc via performance of modern tricks within cities and basic frame work. Modern motion, somehow assumed under the normal condition of living just because of the concentration on the maximum movement of public, faced here to utilize modern ICT to advance inspection as well as transaction units that give us effective, protective, and eco system friendly services for all traveler. On the basis of these terms, different detectors such as local approach, fruitful yield and emissions etc have been operated to give efficient results of the implement of smart cities and favorable decision makers operate terms in such a way even modern municipal (Lin, 2017).

Smart mobility and ITS in the context, differ analysis, estimation, and arrangement as well as control ways that must be carried in rational era depends upon provided data from detectors and contributors. Transportation relevant issues classified in a big digits of independent variables relation which may not acknowledge properly, big covering areas of improper details, improper aims as well as components. In recent time, Related technologies to Al, having own specific power in information establishment that is implemented within modern travelling with ITS. AI explain (Soriguera, 2011; Michalopoulos, 1991). This is to make distinct decisions which able to increase the opportunity of receiving the goal. Usual adopted AI approaches towards transportation issues that include virtual neural cycle of network, vector supported machines, and Bayesian cycle of network (Yang, 2017).

ANN have ability to implement non-linear planning in both inputs and yield by the understanding of behind layers as well as enough practice that are sufficient for the clue about travelling issues that include parametric relationships among different variables which are not able to acknowledge properly. Literature shows that ANNs are usually implemented in analysis conditions/forecasting, incident sensors, traffic/infrastructure boundaries, and attitude of estimation (Pengfei, 2014). Likeness to ANN, support vector equipment acts as look after models of learning which estimate inlet information. By the way these are more concentrate under characterization scale and scenarios. In a consequence, SVMs have been implemented further mobility-relevant issues, they are basically utilized for issues just as incident sensors. The both mechanisms are not similar as above, which are only information-driven, Bayesian cycle is a kind of analytical model which understands the probabilities aswell as situation dependencies related to the restricted variables. Literature of ITS shows that the Bayesian networks utilized for different transport issues just because of basic use when the concentration is traffic augur as well as incident/accident-relevant problems (Day, 2017).

Smart Traffic Mobility Management

There is considerable uniqueness for the smart traffic mobility management that become a basic reason for detecting tricks, the present conditions in the direction such that the mobility of the traffic can be extensively managed. This results in the formation of the Vehicle Authentication and Controlled System. This system appearing as full of efficiently personal protection, ease as well as convenient source, also release in relevant vehicles. It is also assuming that this proposed system will be able to establish stamina which enhance whole travelling capacity via traffic remote. However, daily basis public-piloted that will peruse to do some actions with a basic center part in the marketing through a little period of time. This will manage the traffic in such a way that it will classify the track into CAV as well as RHV(Wang, 2016). By comparing vehicle traffic crowd, walkers considered as the utmost worth able path or track utilizers. They play an efficient and significant part of overall track traffic victim, losses as well as injuries as mentioned that 273,000 walkers were lost in 2010.

Now a days, all work has focus on establishing and managing the unique and modern driver partner unit dependent traveler secured systems. So, the implementation of these systems is really worth able if a complex residential eco system just because of different hard less and improper era for movers to show reaction (Lan, 2014; Fu, 2002; Abdullah, 2015). Vehicle pedestrian communication techniques faced to resolve issues of pedestrian as well as traffic interaction to make is efficient for public protection. The unsettled uniqueness of ICT and enhancement in absorption of modern gadget, concept of a connected eco system in the context that related to transportation has been enlarged. This system will also result in the passing of the restricted areas. The traffic cycle will be managed as directed graphs only related to travel infrastructure. While the traffic way of networks should base of public, perceptual path mentioning, as well as various modal transport systems. So, it become more and more efficient for the acknowledgment of the overall network under cyber security, public attitude and physical gap.

Planning Activities for Future Its and Smart Cities

Reviews giving information in the preceding section, it is seemed that eventual of ITS drop within the numerous surface lines of the allied eco system such as cyber security, social and practical appearance. Present with these comprehensive details, the purpose of this part is to give us few perceptions related to the establishment of future ITSs and modern municipal that involve: examination relevant to the details of cyber origin, CSP cycle modeling as well as moving models in a combined; eco system (Albino, 2015).

Analyzing public attitudes and perceptions from cyber sources

Aside of the corporeal details that make sure to collect by driver detectors, community sentiments as well as expectations assembled through cyber origin such as social networks which are the second optimistic origin of information of data for perception of a town rank also the production of its conveying unit. So that these data sources become able to be used by future ITSs to detect and for system management (Hall, 2000). To take out helpful and efficient data from social network details origin based on algorithm so that it takes on pre elaborated composition which is proposed for information detection. The NLP algorithm is such that it must be able to sense enough social probability and/or private judgment that conduct to high energy traffic crises such as overcrowding after a match of cricket or football, or show people behaviors in the orientation of above mentioned terms and understandings of the travelling unit present required approach (Lombardi, 2012). As well as, with materialistic and spatially labeled networking cycle of information and data, the scope and concerns about traffic crowd crises for example the comments due to pending of train service after an 8 AM can produce disturbance which can easily be measured also (Victoria, 2016).

Modelling of CSP Traffic Networks

For good assimilation of details via CSP gap and further materialize from various origin of information as CSP model be prospered to permit for the consortium of information. A recovery of traffic cycle of model that amalgamates practices, logic based as well as everlasting global in the digital reorganization of CSP gap that must be contemplated in the future. To represent network correspondence, a restricted-layered among cyber, social, and practical appearing layers network couple enabled by brilliant computing inference models. By the use of statistics and NLP, the consortium rule of passing-domain information could be analyzed. For example, the space time correspondence rule must be stable between Bluetooth frequency and traffic covering area, or building force utilization and pedestrian movement (Neirotti, 2014). Composing this recovery of traffic network model, just because of the prosperity with accessible travelling information, it is suspicious to analyze and describe the kinds and amounts in temporal and axis resolution domain of details that have enough to carry out different tasks efficiently (Iker, 2016).

Flow models under connected

Confirmation is done that in coming days ITSs will be implement in coupled eco system with compound CAVs and RHVs with enhancing popularity which is VACS. CAVs are classified in considerably various terminology from of RHVs and it became complex to comprehends the flow classification of these correlated-vehicles eco system for utilizing in ITS.

Enlarge vehicular movement models gives requisite at both the small as well as large level. (Giffinger, 2015) microscopically, recent car moving models able to contemplated with the interaction of accommodation of the CAV-relevant constituents such as improper vehicular communities, communication pending problems, driving agreements, absorption rate of CAVs, etc. Such Car moving model able to use in the manufacturing of link-dependent control in ITS. In opposite, at large scale, the CAV-relevant features should be gathered in establishment of network-flow model to give favor in geographical controlling and management for example controlling the crowding scale of a rational, functioning cordon-dependent scheme of pricing etc. (Shinya, 2009).

Conclusion

For the urban environment, these techniques telecommunications are considered outstanding potentially innovative technologies. Vehicles' presence depends upon pressure variation in the tube that can be detected by different and pneumatic tubes. These terms have been utilized in traffic information to collect bases as showing: traffic volume and spot speed. Traffic data collection is increasingly being considered for scanning video cameras and Radio-Frequency Identification (RFID). To collect proper traffic data video cameras are designed at different stations in the system of the network. Strategies of disposal data and control/management involve various methods from traditional traffic signs and broadcasting of radio to mobile applications. In sort, unique municipal funds having the goal to make more and more efficient the literacy standard and strong youth contribution of citizens via the provision of plenty of knowledge surety through the other parts of the smart society. Connected Digits of Automated Vehicles (CAVs) connected through VACS will quickly enhance the upcoming ten years. In opposite, on a large scale, the CAV-relevant features should be gathered in the establishment of the network-flow model to give favor in geographical controlling and management.

References

  1. Henry X., Xiaozheng, H., &Will, R. (2007). Estimation of the time-dependency of values of travel time and its reliability from loop detector data. Transp. Res. B 41 (4), 448–461.
  2. F. Soriguera, & F. Robuste. (2011). Estimation of traffic stream space mean speed fromtime aggregations of double loop detector data. Transp. Res. C 19 (1), 115–129.
  3. Nordback, K., Kothuri, S., Phillips, T., Gorecki, C., & Figliozzi, M. (2016). Accuracy of bicycle counting with pneumatic tubes in Oregon. Transp. Res. Rec. 2593, 8–17.
  4. Michalopoulos, P.G. (1991). Vehicle detection video through image-processing — The autoscope system. IEEE Trans. Veh. Technol. 40 (1), 21–29.
  5. Fathy, M., Siyal, M.Y. (1998). A window based image processing technique for quantitative and qualitative analysis of road traffic parameters. IEEE Trans. Veh. Technol. 47(4), 1342–1349.
  6. Chang, S.L., Chen, L.S., Chung, Y.C., & Chen, S.W. (2004). Automatic license plate recognition. IEEE Trans. Intell. Transp. Syst. 5 (1), 42–53.
  7. Anagnostopoulos, C.N.E., Anagnostopoulos, I.E., Psoroulas, I.D., Loumos, V., & Kayafas, E. (2008). License plate recognition from still images and video sequences: A survey. Transactions on Intelligent Transportation Systems 9(3), 377–391.
  8. Tam, M.L., Lam, W.H.K. (2008). Using automatic vehicle identification data for travel time estimation in Hong Kong. Transportmetrica 4(3), 179–194.
  9. Li, X.M., William, H.K., & Tam, M.L. (2013). New automatic incident detection algorithmbased on traffic data collected for journey time estimation. ASCE Journal of Transportation Engineering 139(8), 840–847.
  10. Vanajakshi, L., Subramanian, S.C., & Sivanandan, R. (2009). Travel time prediction under heterogeneous traffic conditions using global positioning system data from buses. IET Intell. Transp. Syst. 3 (1), 1–9.
  11. Dihua, S., Luo, H., Liping, F., Liu, W.N., Liao, X.Y., & Zhao, M. (2007). Predicting bus arrival time on the basis of global positioning system data. Transp. Res. Rec. 2034, 62–72.
  12. Ashish, B., & Edward, C. (2013). Fundamental understanding on the use of Bluetooth scanner as a complementary transport data. Transp. Res. C (37), 42–72.
  13. Antonin, D., Bilal, F., & Michel, B. (2014). A Bayesian approach to detect pedestrian destination-sequences from WiFi signatures. Transp. Res. C (44), 146–170.
  14. Caceres, N., Wideberg, J.P., & Benitez, F.G. (2007). Deriving origin-destination data from a mobile phone network. IET Intell. Transp. Syst. 1(1), 15–26.
  15. Calabrese, F., Diao, M., Di Lorenzo, G., Ferreira, J., & Ratti, C. (2013). Understanding individual mobility patterns from urban sensing data: a mobile phone trace example. Transp. Res. C 26, 301–313.
  16. Yang, H., & Huang, H.J. (2004). The multi-class, multi-criteria traffic network equilibrium and systems optimum problem. Transp. Res. B, 38(1), 1–15.
  17. Zhong, A., Sumalee, T.L., Friesz,W.H.K. (2011). Dynamic user equilibrium with sideconstraints for a traffic network: theoretical development and numerical solutionalgorithm. Transp. Res. B, 45(7), 1035–1061.
  18. Zhong, A., Sumalee, T.L., Pan, W.H.K. (2013). Stochastic cell transmission model fortraffic network with demand and supply uncertainties. Transportmetrica A, 9(7), 567–602.
  19. Geroliminis, N., & Daganzo, C.F. (2008). Existence of urban-scale macroscopic fundamental diagrams: some experimental findings. Transp. Res. B, 42(9), 759–770.
  20. Li, J., Yue, Z.Q., & Wong, S.C. (2004). Performance evaluation of signalized urban intersectionsunder mixed traffic conditions by gray system theory. Journal of Transportation Engineering-ASCE 130(1), 113–121.
  21. Liu, H.X., Wu X., Wenteng, M., & Hu, H. (2009). Real-time queue length estimation forcongested signalized intersections. Transp. Res. C, 17(4), 412–427.
  22. Kitamura, R., Chen, C., Pendyala, R.M., & Narayanan, R. (2000). Micro-simulation of daily activity- travel patterns for travel demand forecasting. Transportation, 27(1), 25–51.
  23. Yin, W.H., Murray, P., Ukkusuri, S.V., & Gladwin, H. (2014). An agent-based modeling systemfor travel demand simulation for hurricane evacuation. Transp. Res. C, 42, 44–59.
  24. Siripirote, T., Sumalee, A., Ho, H.W., & Lam, W.H.K. (2015). Statistical approach for activity-basedmodel calibration based on plate scanning and traffic counts data. Transp. Res. B 78: 280–300.
  25. Alena, E., Fridulv,S., & Rolf, H. (2007). Effects of route guidance Variable Message Signs (VMS) on driver behavior. Transp. Res. F, 10(6), 447–457.
  26. Athena, T. (2015). Modeling the impact of traffic information acquisition from mobile devices during the primary tour of the day. J. Intell. Transp. Syst.19(2), 125–133.
  27. Geva,V., David, S., & Yuval, B. (2011). In-vehicle information systems to improve traffic safety in road tunnels. Transp. Res. F, 11(1), 61–74.
  28. Shao, H., Lam, W.H.K., Sumalee, A., & Chen, A. (2017). Network-wide on-line travel time estimation with inconsistent data from multiple sensor systems under network uncertainty. TransportmetricaA 14(1–2), 110–129.
  29. Fu, L.P. (2001). An adaptive routing algorithm for in-vehicle route guidance systems with real-time information, Transp. Res. B 35 (8): 749–765.
  30. Lin, J., Yu, W., Yang, X.Y., Yang, Q.Y., Fu, X.W., & Zhao, W. (2017). A real-time en-route route guidance decision scheme for transportation-based cyberphysical systems. IEEE Trans. Veh. Technol. 66(3), 2551–2566.
  31. Yang, C.F., Ju, Y.H., Hsieh, C.Y., Lin, C.Y., Tsai, M.H., & Chang, H.L. (2017). Iparking — A real-timeparking space monitoring and guiding system. Vehicular Communications 9, 301–305.
  32. Pengfei, Z., Yuanqing, Z., Mo, L. (2014). How long to wait? Predicting bus arrival time with mobile phone based participatory sensing. IEEE Trans. Mob. Comput. 13(6), 1228–1241.
  33. Day, C.M., Li, H., Richardson, L.M., Howard, J., Platte, T., Sturdevant, J.R., & Bullock, D.M. (2017). Detector-free optimization of traffic signal offsets with connected vehicle data. Transp. Res. Rec. 2620, 54–68.
  34. Wang, M., Daamen, W., Hoogendoorn, S.P., & Van Arem, B. (2016). Connected variable speed limits control and car-following control with vehicle-infrastructure communication to resolve stop-and-go waves. J. Intell. Transp. Syst. 20(6), 559–572.
  35. Lan, J., Hani, S. (2014). City logistics freight distribution management with time dependent travel times and disruptive events. Transp. Res. Rec. 2410, 85–95.
  36. Fu, L.P., & Yang, X.H. (2002). Design and implementation of bus-holding control strategies with real-time information. Transp. Res. Rec.1791, 6–12.
  37. Abdullah, K., Ender, F., & Kaan, O. (2015). Extended implementation method for virtual sensors web-based real-time transportation data collection and analysis for incident management. Transp. Res. Rec. 2528, 27–37.
  38. Tuan-Yee C., Ferreira, J. (2015). Smart cities: Concepts, perceptions and lessons for planners, in: S. Geertman Jr., J. Ferreira, R. Goodspeed, J. Stillwell (Eds.) (2015). Planning Support Systems and Smart Cities, Lecture Notes in Geoinformation and Cartography, Springer, Cham, pp. 145–168.
  39. Vito, A., Umberto, B., & Rosa, M. (2015). Smart cities: Definitions, dimensions, performance, and initiatives. Journal of Urban Technology, 22(1), 3–21.
  40. Hall, R.E. (2000). The Vision of a Smart City. Proceedings of the 2nd International Life ExtensionTechnology Workshop, Paris, France.
  41. Lombardi, P., Giordano, S., Farouh, H., & Yousef, W. (2012). Modelling the smart city performance. Innovation-The European Journal of Social Science Research,s 25(2), 137–149.
  42. Victoria, A. (2000). Stakeholders approach to smart cities: A survey on smart city definitions, in: E. Alba, F. Chicano, G. Luque (Eds.), Smart Cities. Smart-CT 2016, Lecture Notes in Computer Science, 9704, Springer, Cham, pp. 157–167.
  43. Neirotti, P., De Marco, A., Cagliano, A.C., Mangano, G., & Scorrano, F. (2014). Current trends in smart city initiatives: some stylised facts, Cities, 38, 25–36.
  44. Iker, Z., Alessandro, S., & Saioa, A. (2016). Smart city concept: What it is and what it should be. Journal of Urban Planning and Development, 142(1), 04015005.
  45. Giffinger, R., Gudrun, H. (2010). Smart cities ranking: An effective instrument for the positioning of cities? ACE Architecture, City and Environment, 4(12), 7–25.
  46. Shinya Kikuchi(2009). Artificial intelligence in transportation analysis: approaches, methods, and applications, Transp. Res. C, 17(5), 455.
Get the App