Anomaly detection and classification in traffic flow data from fluctuations in the flow–density relationship

Kalair, Kieran; Connaughton, Colm

doi:10.1016/j.trc.2021.103178

Cited by 29 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The headway distribution of simulated traffic follows a negative exponential distribution. To simulate the heterogeneity of traffic flow, we referred to the statistics of real traffic [44, 45] and assumed that the initial speed

\;v_n^0{\rm{\;}}

(in metres per second) of each generated vehicle follows a normal distribution, that is,

v_n^0

∼ N (20, 3 2 ); the desired speed also follows a normal distribution,

{\rm{\;}}v_n^d

∼ N (25, 3.35 2 ). Under such speed distributions, the desired speeds of most vehicles are in the range of 80–120 km/h, which is consistent with real‐world freeway traffic conditions.…”

Section: Resultsmentioning

confidence: 99%

Cyberattacks on connected automated vehicles: A traffic impact analysis

Sun

Liu

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Cybersecurity has become one of the major challenges for Connected Automated Vehicles. Previous work in this field mostly focused on the detection of and defence against Connected Automated Vehicle‐related cyberattacks. Using performance measures collected from traffic micro‐simulations, the study analysed the traffic impacts of cyberattacks on Connected Automated Vehicles. Two types of adversary models, namely, time‐delay attacks and disturbance attacks, were applied to the simulated traffic on freeway segments and un‐signalised intersections, respectively. The effects of various cyberattacks were evaluated based on safety indicators, including Time‐To‐Collision, Deceleration Rate to Avoid Collision, and efficiency indicators, including speed and flow‐density diagrams. The results revealed that both attacks increase the risk and severity of collisions on freeway segments and un‐signalised intersections. Location‐based time‐delay attacks will result in significant deceleration, congestion and reduction in road throughput. Disturbance attacks not only cause congestion but also result in frequent acceleration/deceleration and uneven distribution of traffic density. The impacts of attacks are more severe on heavy traffic. At un‐signalised intersections, location‐based disturbance attacks lead to a significantly increased risk of right‐angled collisions. The results could help better understand the effects of Connected Automated Vehicle‐related cyberattacks and shed light on proactive defence against such attacks.

show abstract

\;v_n^0{\rm{\;}}

(in metres per second) of each generated vehicle follows a normal distribution, that is,

v_n^0

∼ N (20, 3 2 ); the desired speed also follows a normal distribution,

{\rm{\;}}v_n^d

∼ N (25, 3.35 2 ). Under such speed distributions, the desired speeds of most vehicles are in the range of 80–120 km/h, which is consistent with real‐world freeway traffic conditions.…”

Section: Resultsmentioning

confidence: 99%

Cyberattacks on connected automated vehicles: A traffic impact analysis

Sun

Liu

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…There are three standard and commonly used performance metrics in the literature; 50‐52 the DR, the FAR and the MTTD. The Detection Rate (DR) is the percentage of the correctly detected congestions, formally:

DR = No.

…”

Section: Traffic Congestion Detection (Tcd) Algorithmmentioning

confidence: 99%

“…There are three standard and commonly used performance metrics in the literature; [50][51][52] the DR, the FAR and the MTTD.…”

Section: Traffic Congestion Detection Performance Metricsmentioning

confidence: 99%

Novel traffic congestion detection algorithms for smart city applications

Bawaneh

Simon

2022

Concurrency and Computation

View full text Add to dashboard Cite

Traffic congestion detection (TCD) techniques are becoming a critical component of traffic management systems. They can be considered a pre-step to address traffic jam problems, providing useful input for traffic management systems to predict and avoid traffic congestions' unwanted effects. In this research article, two novel real-time congestion detection algorithms are proposed, the TCD algorithm and the ensemble based traffic congestion detection (EB-TCD) algorithm. TCD can detect the congestion based on one traffic feature (i.e., speed, occupancy, or flow). TCD first cleans and preprocesses the traffic data. After, it computes the absolute of the first derivative of each sample in the traffic feature to determine its anomaly score. Then, the anomaly likelihood of each sample is computed to classify it as an anomaly or normal sample. On the other hand, EB-TCD utilizes the information contained in multiple traffic features in parallel by proposing an ensemble technique to combine the anomaly scores coming out from the different traffic features in one unified score. EB-TCD computes an anomaly score based on each traffic feature separately. Then, it votes for each sample in each traffic feature as an anomaly or not (from the corresponding traffic feature's point of view). After, the weight for each traffic feature is determined by studying the dissimilarity between their anomaly scores. These weights show how much each traffic feature explains the traffic behavior. Finally, the results are combined to form a unified anomaly score for each sample. The proposed statistical-based techniques are able to detect changes in traffic patterns while mitigating the effect of noise in traffic data. Moreover, the proposed algorithms' parameters were tuned and tailored for fast detection, which is a crucial feature for traffic management systems since fast detection accelerates decision-making. The computational complexity analysis has shown the simplicity of the proposed algorithms. Furthermore, the evaluation results have shown that the two algorithms outperform other widespread methods from the literature in terms of false alarm rate and detection time while keeping the detection rate at the same high level.

show abstract

“…After, we account for any potential missing incident flags by further removing any remaining periods with a severity higher than 0.3. Severity is defined as in Kalair and Connaughton (2020), which in short, considers the joint behavior of the speed-flow time-series and questions what points correspond to large fluctuations from a region of typical behavior in this relationship. We then take this filtered series and extract the seasonal components, in our case daily and weekly components, to capture natural variability on the link.…”

Section: Data Collection and Processingmentioning

confidence: 99%

Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations

Kalair

Connaughton

2021

Front. Future Transp.

Self Cite

View full text Add to dashboard Cite

Understanding and predicting the duration or “return-to-normal” time of traffic incidents is important for system-level management and optimization of road transportation networks. Increasing real-time availability of multiple data sources characterizing the state of urban traffic networks, together with advances in machine learning offer the opportunity for new and improved approaches to this problem that go beyond static statistical analyses of incident duration. In this paper we consider two such improvements: dynamic update of incident duration predictions as new information about incidents becomes available and automated interpretation of the factors responsible for these predictions. For our use case, we take one year of incident data and traffic state time-series data from the M25 motorway in London. We use it to train models that predict the probability distribution of incident durations, utilizing both time-invariant and time-varying features of the data. The latter allow predictions to be updated as an incident progresses, and more information becomes available. For dynamic predictions, time-series features are fed into the Match-Net algorithm, a temporal convolutional hitting-time network, recently developed for dynamical survival analysis in clinical applications. The predictions are benchmarked against static regression models for survival analysis and against an established dynamic technique known as landmarking and found to perform favourably by several standard comparison measures. To provide interpretability, we utilize the concept of Shapley values recently developed in the domain of interpretable artificial intelligence to rank the features most relevant to the model predictions at different time horizons. For example, the time of day is always a significantly influential time-invariant feature, whereas the time-series features strongly influence predictions at 5 and 60-min horizons. Although we focus here on traffic incidents, the methodology we describe can be applied to many survival analysis problems where time-series data is to be combined with time-invariant features.

show abstract

Anomaly detection and classification in traffic flow data from fluctuations in the flow–density relationship

Cited by 29 publications

References 38 publications

Cyberattacks on connected automated vehicles: A traffic impact analysis

Cyberattacks on connected automated vehicles: A traffic impact analysis

Novel traffic congestion detection algorithms for smart city applications

Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations

Contact Info

Product

Resources

About