Multiple Sensors Data Integration for Traffic Incident Detection Using the Quadrant Scan

Zaitouny, Ayham; Fragkou, Athanasios D.; Stemler, Thomas; Walker, David M.; Sun, Yuchao; Karakasidis, Theodoros E.; Nathanail, Eftihia; Small, Michael

doi:10.3390/s22082933

Cited by 6 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a vast amount of further directions of the present work, which at present the authors are pursuing. For example, advanced machine learning methods can be employed for putting in connection the measurement channels related to the rotor and the blade pitch to the observed power: in particular, clustering methods [33] and multivariate data integration methods [34] could be useful for interpreting the results more in depth.…”

Section: Abbreviationsmentioning

confidence: 99%

Discussion of Wind Turbine Performance Based on SCADA Data and Multiple Test Case Analysis

Astolfi

Pandit

Terzi³

et al. 2022

Energies

View full text Add to dashboard Cite

This work is devoted to the formulation of innovative SCADA-based methods for wind turbine performance analysis and interpretation. The work is organized as an academia–industry collaboration: three test cases are analyzed, two with hydraulic pitch control (Vestas V90 and V100) and one with electric pitch control (Senvion MM92). The investigation is based on the method of bins, on a polynomial regression applied to operation curves that have never been analyzed in detail in the literature before, and on correlation and causality analysis. A key point is the analysis of measurement channels related to the blade pitch control and to the rotor: pitch manifold pressure, pitch piston traveled distance and tower vibrations for the hydraulic pitch wind turbines, and blade pitch current for the electric pitch wind turbines. The main result of this study is that cases of noticeable under-performance are observed for the hydraulic pitch wind turbines, which are associated with pitch pressure decrease in time for one case and to suspected rotor unbalance for another case. On the other way round, the behavior of the rotational speed and blade pitch curves is homogeneous and stable for the wind turbines electrically controlled. Summarizing, the evidence collected in this work identifies the hydraulic pitch as a sensible component of the wind turbine that should be monitored cautiously because it is likely associated with performance decline with age.

show abstract

Section: Abbreviationsmentioning

confidence: 99%

Discussion of Wind Turbine Performance Based on SCADA Data and Multiple Test Case Analysis

Astolfi

Pandit

Terzi³

et al. 2022

Energies

View full text Add to dashboard Cite

show abstract

“…Simulation results showed 30% faster detection compared with other methods. Zaitouny et al [17] proposed a Quadrant Scan methodology as a tool to analyse traffic volume data to detect incidents by integrating multiple sensors' data. e proposed method also distinguishes nonrecurrent traffic congestion caused by incidents from recurrent congestion.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Incident-Responsive Signal Control Strategy under Partially Connected Vehicle Environment

Chandan

Seco

Silva

2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

The performance of the traffic system can drastically drop when nonrecurrent congestion caused by incidents occurs. Early detection and clearing of traffic incidents will enable the mitigation of the congestion and early restoration of normal traffic conditions. The research in this paper utilized the vehicle information from the recent technological advancement in transportation systems, connected vehicles (CV), and loop-detector information for nonconnected vehicles (NCVs) and developed a novel algorithm to (1) control traffic signals for normal traffic conditions in the absence of incidents, (2) detect traffic incidents using CV/NCV information, and (3) control traffic signals during the occurrence and dissipation of incidents. All the 3 strategies were integrated into one algorithm, which runs as per the real-time traffic conditions, in the presence or absence of incidents. Space-mean speeds of the vehicles on nonincident lanes and throughput maximization criteria were taken as the indicators for the activation of specific signal timings directed at the incident-affected approach. Diverse incident scenarios were tested on a four-legged isolated intersection using the VISSIM simulation tool. Incident detection results showed a higher detection rate and lower mean detection time at higher CV penetration and higher traffic volumes, and at the incident locations nearer to the stop-line. The proposed incident-responsive signal control strategy at 40% and higher CV penetration showed better performance over EPICS adaptive signal control solution, in reducing average travel time delay and the average number of stops per vehicle.

show abstract

Detecting criticality in complex univariate time-series: A case study of the U.S. housing market crisis and other markets

Harré¹,

Zaitouny²

2023

Expert Systems with Applications

View full text Add to dashboard Cite

Multiple Sensors Data Integration for Traffic Incident Detection Using the Quadrant Scan

Cited by 6 publications

References 54 publications

Discussion of Wind Turbine Performance Based on SCADA Data and Multiple Test Case Analysis

Discussion of Wind Turbine Performance Based on SCADA Data and Multiple Test Case Analysis

Real-Time Incident-Responsive Signal Control Strategy under Partially Connected Vehicle Environment

Detecting criticality in complex univariate time-series: A case study of the U.S. housing market crisis and other markets

Contact Info

Product

Resources

About