Learning Non-cooperative Driving Practices and its Impact on Road Traffic Dynamics

COMSNETS [Poster Track]

Paper link:   [click here]

Publication Year:  2024

Cooperative driving that prioritizes global safety and efficiency over self-interest is crucial in ensuring smooth traffic flow and enhanced road safety. However, experiencing non-cooperative driving is common under heterogeneous and chaotic on-road traffic conditions. While we often assess non-cooperativeness during direct vehicle interactions, we can infer it through longitudinal analysis of driving patterns from vehicular kinematics data. This behavior not only adversely affects the vehicle itself but also has a cascading impact on nearby vehicles, ultimately disrupting overall traffic flow. In this study, we quantify a vehicle's non-cooperativeness using kinematic data and further model its cascading effects on nearby cooperative vehicles. We conducted an experimental analysis using the SUMO traffic simulator and the TraCI interface to evaluate the impact of non-cooperativeness on overall traffic dynamics. This research is among the first to examine the cascading effects of a vehicle's non-cooperativeness on its cooperative nearby vehicles.

A Cost-Sensitive LSTM Model for Driving Risk Assessment from Vehicular Trajectory Data

IEEE VTC-Fall (100th Edition)

Paper link:    [click here]

Publication Year:  2024

Identifying risky driving behavior is crucial for early hazard detection, encouraging safer driving practices, and minimizing accident risks. Sensory data characterized by driving patterns can classify risky behavior. However, effective classification into risk categories relies on supervised learning methods that require labeled data. The challenge lies in the high cost and difficulty of obtaining accurate ground-truth labels for these signatures. As a result, most datasets lack risk labels. Additionally, because risky incidents are infrequent during regular driving, the dataset collected from studies becomes imbalanced, containing fewer instances of risky events. This imbalance poses a significant challenge, as it biases the model towards the majority class, increasing the likelihood of costly misclassifications where risky instances are incorrectly identified as safe. To address this, we propose a three-stage method. First, we identify driving events indicative of risky behavior from the trajectory data and mathematically formulate them as potential risk indicators. Using these indicators, we then employ clustering to assign appropriate risk labels to the data. Lastly, we fix the class imbalance issue with a cost-sensitive LSTM model. This model uses a custom loss function and LSTM architecture to sort instances into risky groups first correctly. Our method outperforms other state-of-the-art approaches with high accuracy, precision, F1 score, and recall of 98.13%, 95.2%, 96.6%, and 96.35%, respectively, effectively managing an imbalanced dataset.

Hybrid Mode of Operations for RPL in IoT: A Systematic Survey

IEEE Transactions on Network and Service Management

Paper link:  [click here]

Publication Year:  2022

RPL (Routing Protocol for Low-Power and Lossy Networks) is a crucial and widely accepted routing protocol for the Internet of Things (IoT). RPL constructs something similar to a tree structure for data routing. For efficient routing, RPL offers a different mode of operation to satisfy different applications effectively. We are considering several approaches and parameters, including other factors, in this paper that contribute to designing the hybrid mode of operations. This paper provides a comprehensive and systematic survey of various hybrid modes of operation for RPL. We outline the challenges and methodologies in the pseudocode format and subsequently analyze all the possible format properties with different network conditions. 

Cite: Mishra, A. K., Singh, O., Kumar, A., & Puthal, D. (2022). Hybrid mode of operations for rpl in iot: A systematic survey. IEEE Transactions on Network and Service Management, 19(3), 3574-3586. 

Hybrid Mode of Operation Schemes for P2P Communication to Analyze End-Point Individual Behaviour in IoT