Using Heart Rate and Machine Learning for VR Horror Game Personalization

In this paper, we explore if we can personalize horror games in Virtual Reality using auditory and visual stimuli with the help of different machine learning algorithms. Based on the heart rate of the subjects we personalize the sound and lighting effects of the game in two different environmental settings. Gradient Boosted Tree Regression, Random Forest Regression, and Tree Ensemble Regression were used to predict which sound and lighting effects should be used in subsequent levels to increase the horror aspect. In order to have a realistic game experience and due to the ongoing coronavirus pandemic, participants were recruited online. Participants could play the game wherever and whenever they wanted. The participants were also asked to complete Self-Assessment Manikin tests after playing the game. We present our discussions and observations of how different factors affect the heart rate in the game and if the heart rate data aligns with the participant's Self-Assessment Manikin test data. © 2022 IEEE.

Spatio-Temporal Characteristics of Air Quality Index (AQI) over Northwest China

In recent years, air pollution has become a serious threat, causing adverse health effects and millions of premature deaths in China. This study examines the spatial-temporal characteristics of ambient air quality in five provinces (Shaanxi (SN), Xinjiang (XJ), Gansu (GS), Ningxia (NX), and Qinghai (QH)) of northwest China (NWC) from January 2015 to December 2018. For this purpose, surface-level aerosol pollutants, including particulate matter (PMx, x = 2.5 and 10) and gaseous pollutants (sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and ozone (O-3)) were obtained from China National Environmental Monitoring Center (CNEMC). The results showed that fine particulate matter (PM2.5), coarse particulate matter (PM10), SO2, NO2, and CO decreased by 28.2%, 32.7%, 41.9%, 6.2%, and 27.3%, respectively, while O-3 increased by 3.96% in NWC during 2018 as compared with 2015. The particulate matter (PM2.5 and PM10) levels exceeded the Chinese Ambient Air Quality Standards (CAAQS) Grade II standards as well as the WHO recommended Air Quality Guidelines, while SO2 and NO2 complied with the CAAQS Grade II standards in NWC. In addition, the average air quality index (AQI), calculated from ground-based data, improved by 21.3%, the proportion of air quality Class I (0-50) improved by 114.1%, and the number of pollution days decreased by 61.8% in NWC. All the pollutants' (except ozone) AQI and PM2.5/PM10 ratios showed the highest pollution levels in winter and lowest in summer. AQI was strongly positively correlated with PM2.5, PM10, SO2, NO2, and CO, while negatively correlated with O-3. PM10 was the primary pollutant, followed by O-3, PM2.5, NO2, CO, and SO2, with different spatial and temporal variations. The proportion of days with PM2.5, PM10, SO2, and CO as the primary pollutants decreased but increased for NO2 and O-3. This study provides useful information and a valuable reference for future research on air quality in northwest China.