This study focused on whether predicting the game outcome prior to watching the actual game results in more positive evaluations of game consumption from sports fans through heightened perceived curiosity and flow. This study employed a 4 (prediction type: no prediction vs. simple prediction vs. prediction and compete against AI vs. prediction and compete against other fans) × 2 (game outcome: winning vs. losing) between-subjects design. The results suggest that fans who make predictions about the outcome before watching highlight videos experience greater feelings of curiosity and flow, and more positive evaluations of game consumptions in comparison to those who do not make any predictions prior to watching the game. Our findings not only contribute to fan behavior and human-computer interaction literature by examining the role of prediction and curiosity but also offer meaningful practical implications for developing effective fan engagement interfaces by incorporating the elements of prediction and competition.

By integrating the construal level theory (CLT) and explainable artificial intelligence (XAI) framework, this study identified personal innovativeness (PI) as a key user trait and different sequences of data presentation as key interfaces of an XAI system that determines how users evaluate and accept recommendations received from XAI. Based on CLT, the results of Study 1 identified the degree of psychological distance that users form with AI technology as a key underlying mechanism that explains the positive effects of users’ PI on their evaluation of AI recommendation systems. From the perspective of XAI, the results of Study 2 further demonstrated that users’ evaluations of XAI recommendation systems are determined by their level of PI and how the XAI interface presents information to them (i.e., whether the explanation comes first and is then followed by a decision or vice versa). The results of this study provide several meaningful theoretical and practical implications for human-AI interactions.

This study examined whether exposing individuals to an age-morphed image of their future selves has positive impacts on physical activity and healthy eating intentions depending on the level of self-esteem. In this study, a 2 (type of future self: age-morphed image vs. simple imagination of future self) × 2 (self-esteem: low vs. high) experimental design was used, where the type of future self was manipulated while self-esteem was measured. The results suggested that individuals with high self-esteem exposed to future selves via age-morphing technology more concretely perceived their future selves and thus showed greater intention to engage in physical activity in the future than those who simply imagined their future selves. Meanwhile, the positive effects of an age-morphed image on future intention to engage in physical activity were not found for low self-esteem individuals. Moreover, the age-morphing technology did not impact individuals’ healthy eating intentions.

For realizing safe autonomous driving, the end-to-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays, surprisingly little attention has been paid to their end-to-end delays from an object's appearance until its detection is reported. With this motivation, this paper aims to provide more comprehensive understanding of the end-to-end delay, through which precise best- and worst-case delay predictions are formulated, and three optimization methods are implemented: (i) on-demand capture, (ii) zero-slack pipeline, and (iii) contention-free pipeline. Our experimental results show a 76% reduction in the end-to-end delay of Darknet YOLO (You Only Look Once) v3 (from 1070 ms to 261 ms), thereby demonstrating the great potential of exploiting the end-to-end delay analysis for autonomous driving. Furthermore, as we only modify the system architecture and do not change the neural network architecture itself, our approach incurs no penalty on the detection accuracy.