Browsing by Author "Ji, Hong-Ming"

Now showing 1 - 3 of 3

A Novel Cue-Induced Abdominal Reaction Analysis for Internet Gaming Disorder
(2019-04-01)
Ji, Hong-Ming
;
Hsiao, Tzu-Chien
;
交大名義發表
;
資訊工程學系
;
資訊科學與工程研究所
Individuals with Internet gaming disorder (IGD) frequently play online games to achieve satisfaction. Numerous signal processing questions regarding the negative consequences and characteristic respiration in a long-term sitting posture remain unanswered. This study recruited 50 individuals with high-risk and low-risk IGD (HIGD and LIGD); these participants were taught to perform a specific respiration during game-film stimuli. The instantaneous frequencies on abdominal movement (f(DF)) were calculated with ensemble empirical mode decomposition (EEMD). The difference value (f(DF)) between rest and stimulus statuses was calculated and found that HIGD showed f(DF) values of 0.060 during positive stimuli and 0.055 during negative stimuli before the exercise but 0.020 and 0.016, respectively, after the exercise. However, the f(DF) value for those with LIGD during negative stimuli before the exercise was 0.013, and it increased to 0.025 after the exercise. This is the first approach to IGD discrimination toward abdominal response with EEMD.
Real-Time Detection of Internet Addiction Using Reinforcement Learning System
(2019-01-01)
Ji, Hong-Ming
;
Chen, Liang-Yu
;
Hsiao, Tzu-Chien
;
資訊工程學系
;
資訊科學與工程研究所
Since Internet addiction (IA) was reported in 1996, research on IA assessment has attracted considerable interest. The development of a real-time detector system can help communities, educational institutes, or clinics immediately assess the risk of IA in Internet users. However, current questionnaires were designed to ask Internet users to self-report their Internet experiences for at least 6 months. Physiological measurements were used to assist questionnaires in the shortterm assessment of IA, but physiological properties cannot assess IA in real-time due to a lack of algorithms. Therefore, the real-time detection of IA is still a work in progress. In this study, we adopted an extended classifier system with continuous real-coded variables (XCSR), which can solve the non-Markovian problem with continuous real-values to produce optimal policy, and determine high-risk and low-risk IA using Chen Internet addiction scale (CIAS) data or respiratory instantaneous frequency (IF) components of Internet users as input information. The result shows that the classification accuracy of XCSR can reach close to 100%. We also used XCSR to verify the items of CIAS and extract important respiratory indexes to assess IA. We expect that a real-time detector that immediately assesses the risk of IA may be designed in this way.
Respiratory Feature Extraction in Emotion of Internet Addiction Abusers Using Complementary Ensemble Empirical Mode Decomposition
(2015-04-01)
Hsieh, Dai-Ling
;
Ji, Hong-Ming
;
Hsiao, Tzu-Chien
;
Yip, Bak-Sau
;
分子醫學與生物工程研究所
Background: Internet addiction can be generally conceptualized as excessive computer and Internet use which results in negative consequences in physical or mental functions. In recent years, Internet addiction is a growing problem around the world, and should be studied through scientific methods. Some studies indicated that Internet addiction was correlated to physical responses including heart rate, respiration, and psychological reactions including emotion, social interaction. This study assumed that emotion was one of significant roles in Internet addiction, and emotion can be observed by subjective self-report and objective autonomic nervous responses. Respiration can be a type of biofeedback to regulate respiratory rate and amplitude which affects autonomic nervous responses. The respiratory features in emotion states of Internet addiction abusers were investigated by Complementary Ensemble Empirical Mode Decomposition. Results: The results showed that the respiratory features of Internet addiction abusers differed from normal Internet users among different emotions. Such results could be expected to monitor or assist to treat Internet addiction.