Vehicle Interaction Behavior Prediction with Self-Attention

The structured road is a scene with high interaction between vehicles, but due to the high uncertainty of behavior, the prediction of vehicle interaction behavior is still a challenge. This prediction is significant for controlling the ego-vehicle. We propose an interaction behavior prediction model based on vehicle cluster (VC) by self-attention (VC-Attention) to improve the prediction performance. Firstly, a five-vehicle based cluster structure is designed to extract the interactive features between ego-vehicle and target vehicle, such as Deceleration Rate to Avoid a Crash (DRAC) and the lane gap. In addition, the proposed model utilizes the sliding window algorithm to extract VC behavior information. Then the temporal characteristics of the three interactive features mentioned above will be caught by two layers of self-attention encoder with six heads respectively. Finally, target vehicle’s future behavior will be predicted by a sub-network consists of a fully connected layer and SoftMax module. The experimental results show that this method has achieved accuracy, precision, recall, and F1 score of more than 92% and time to event of 2.9 s on a Next Generation Simulation (NGSIM) dataset. It accurately predicts the interactive behaviors in class-imbalance prediction and adapts to various driving scenarios.

Value co-creation for developing cultural and creative virtual brand communities

PurposeThis study aims to explore the value co-creation for developing cultural and creative virtual brand communities (CCVBCs) by developing a conceptual framework based on the stimulus-organism-response framework, social cognition theory (SCT) and social exchange theory (SET).Design/methodology/approachThe proposed conceptual framework was developed from a comprehensive review of the related literature. This study tested and validated the proposed framework using partial least square structural equation model based on the data collected through a survey.FindingsFirst, perceived hedonic benefit was positively affected by content personalization, user interaction design and technological innovation. Perceived social benefit and perceived self-achievement benefit were positively affected by user interaction design and technological innovation. Second, user content creation behavior was affected by perceived social benefit and perceived self-achievement benefit; user browsing behavior was significantly affected only by perceived hedonic benefit, and interaction behavior was significantly affected by perceived hedonic benefit, perceived social benefit and perceived self-achievement benefit. Third, perceived social benefit and perceived self-achievement benefit partially mediated the relationship between user interaction design and interaction behavior. As for the influence of technological innovation on interaction behavior, however, and the influence of user interaction design and technological innovation on content creation behavior, both perceived social benefit and perceived self-achievement benefit had complete mediation.Originality/valueThis study found that the characteristics of developing CCVBCs affected perceived benefit in participating in the value co-creation process. The results contributed to the value creation research by enriching the understanding of user value co-creation in developing CCVBCs.

Prefrontal-amygdalar oscillations related to social interaction behavior in mice

The medial prefrontal cortex and amygdala are involved in the regulation of social behavior and associated with psychiatric diseases but their detailed neurophysiological mechanisms at a network level remain unclear. We recorded local field potentials (LFPs) from the dorsal medial PFC (dmPFC) and basolateral amygdala (BLA) while mice engaged on social behavior. We found that in wild-type mice, both the dmPFC and BLA increased 4–7 Hz oscillation power and decreased 30–60 Hz power when they needed to attend to another target mouse. In mouse models with reduced social interactions, dmPFC 4–7 Hz power further increased especially when they exhibited social avoidance behavior. In contrast, dmPFC and BLA decreased 4–7 Hz power when wild-type mice socially approached a target mouse. Frequency-specific optogenetic manipulations of replicating social approach-related LFP patterns restored social interaction behavior in socially deficient mice. These results demonstrate a neurophysiological substrate of the prefrontal cortex and amygdala related to social behavior and provide a unified pathophysiological understanding of neuronal population dynamics underlying social behavioral deficits.