LLLinjun Liu

Linjun Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Linjun Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Psychophysiological restoration in nature: a randomized controlled trial investigating the cognitive, affective, and physiological benefits of green exercise

    by Sheng Yan, Linjun Liu, Zongdi Zhao, Yun Li

    The escalating pace of urbanization has made chronic stress and attentional fatigue significant public health challenges. This study employed a randomized controlled trial ([Formula: see text]) to investigate the psychophysiological restorative effects of a standardized 30-minute walk in an urban forest environment (Outdoor Green) compared to a laboratory setting (Indoor Control). Cognitive function was assessed via the Digit Span Task, affective states were evaluated using the Profile of Mood States (POMS) and self-esteem measures, and physiological stress responses were objectively quantified through salivary cortisol and heart rate variability (HRV-RMSSD). Results indicated that the Outdoor Green group exhibited significantly greater improvements in directed attention ([Formula: see text]) and total mood disturbance ([Formula: see text]) compared to the Indoor Control group. Physiologically, the outdoor group showed a more pronounced reduction in salivary cortisol (interaction [Formula: see text]) and a greater increase in parasympathetic activity (HRV-RMSSD, interaction [Formula: see text]). Furthermore, mediation analysis revealed that the alleviation of negative affective states partially mediated the relationship between environmental exposure and cognitive restoration. These findings demonstrate that green exercise exerts synergistic benefits across cognitive, affective, and physiological domains, providing robust evidence for nature-based interventions as effective strategies for mental health promotion.


  • Open Access

    Artificial Intelligence in UFC Outcome Prediction and Fighter Strategies Optimaztion

    by Sheng Yan, Linjun Liu, Comite Ubaldo

    AI has been more and more widely applied in sports industry, from match outcome prediction, to tacticle decision making, from helping referee to make more precise decision to help the athelete to prevent the potential injury. This study focuses on how to use machine learning predicting the match outcome and identifying the influential factors impacting the outcome in UFC, one of the most money ball game. The dataset utilized in the study covers every match from March 1994 to March 2021, with over 100 variables of the information about the two fighters in the ring, which are suitable to be processed by machine learning methods. Random Forest, Gradient Boosting Decision Tree(GBDT), Support Vector Machines(SVM) are adopted to predict the match outcome and identify the top 10 most important features. Performance metrics such as accuracy, Cohen's kappa, sensitivity, and specificity were used for comparison. Random Forest and GBDT achieved improvement with important features only, whereas, SVM declined in both accuracy and reliability. Although findings of the top 10 important features varied across the models, but the date when the fight took place the age difference between two fighters are top2 in all three models.

  • Optimizing Fighter Strategies and Predicting Outcomes in Bellator MMA Using Artificial Intelligence

    by Sheng Yan, Linjun Liu

    Artificial intelligence (AI) has seen significant growth in sports applications, ranging from outcome prediction and tactical decision support to enhancing referee precision and preventing athlete injuries. This study investigates the use of machine learning algorithms to forecast the results of Bellator MMA matches and identify the key determinants affecting these outcomes. The dataset, comprising over 300 bouts held between 2010 and 2016, offers detailed fighter statistics ideal for machine learning analysis. We applied Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and Support Vector Machines (SVM) to predict match results and highlight the top 10 influential features. Performance comparisons, based on metrics such as accuracy, Cohen's kappa, sensitivity, and specificity, indicated that RF and GBDT improved when using selected key features, whereas SVM showed reduced accuracy and stability. Despite variations in feature importance across models, fight date and age differences between fighters consistently ranked among the top three.