跳到主要內容

臺灣博碩士論文加值系統

(44.192.94.177) 您好!臺灣時間:2024/07/17 01:02
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:田侑霖
研究生(外文):Tien, You-Lin
論文名稱:調整式XCSR於呼吸資訊辨認不同風險程度之網路遊戲成癮症
論文名稱(外文):A Modified XCSR to identify Different Risk level of Internet Gaming Disorder through Respiratory Information
指導教授:蕭子健蕭子健引用關係
指導教授(外文):Hsiao, Tzu-Chien
口試委員:于天立陳穎平紀虹名
口試日期:2021-12-07
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:生醫工程研究所
學門:工程學門
學類:生醫工程學類
論文種類:學術論文
論文出版年:2021
畢業學年度:110
語文別:中文
論文頁數:75
中文關鍵詞:網路遊戲成癮症時序呼吸訊號機器學習擴展式學習分類器
外文關鍵詞:Internet Gaming DisorderTime-series Respiratory signalMachine LearningXCSR
相關次數:
  • 被引用被引用:0
  • 點閱點閱:177
  • 評分評分:
  • 下載下載:8
  • 收藏至我的研究室書目清單書目收藏:0
在網路普及的現代,網路遊戲成癮症(Internet Gaming Disorder, IGD)逐漸成為隱憂,美國精神醫學學會在2013 年將IGD納入《精神疾病診斷與統計手冊第五版》的「需進一步研究對象名單」中。臨床上多採用楊氏網路成癮問卷與陳氏網路成癮量表等回溯性問卷來輔助臨床診斷,然而觀察期長達一年的回溯性問卷可能不利於臨床上即時診斷,除追蹤不易,抑有可能產生記憶混淆。因此利用電腦分析較為客觀的生理訊號方式,藉此輔助判斷高風險IGD(High-risk IGD, HIGD)與低風險IGD (Low-risk IGD, LIGD)相關研究逐漸受到關注,其中觀察IGD遊玩遊戲時的呼吸調控機制,特別是在時序上的變化尤為引人興趣。
為了觀察HIGD與LIGD的呼吸模式在時序上的調控變化,本研究將受測者接受遊戲影片刺激時所截取到的呼吸訊號轉換為不同的呼吸分析資訊(Analytic Signal, AS)包含呼吸訊號之本質模態函數(Intrinsic Mode Function, IMF)、瞬時呼吸頻率(Instantaneous Frequency, IF)以及兩者之比值(IMF/IF),並且以序列標籤問題模式編碼之,受測者依照問卷填寫之分數分為HIGD與LIGD兩群。然而時間序列的問題處於實數、雜訊、複雜等特性的解答空間,若模型無法分辨相同個體在不同時間的狀態將導致效能下降。雖然傳統擴展式學習分類器(eXtended Classifier System with continuous Real-coded variables, XCSR)的機器學習方法擁有良好的知識擷取與解讀架構,但無法分辨相同個體在不同時間的狀態與時序間的關聯性。因此本研究引入了帶有時間標籤的擴展式學習分類器(XCSRtimetag),以時間標籤作為分類器演化方向之指引,幫助系統學習時間序列問題,後續利用重構組件重構訊號,尋找HIGD與LIGD呼吸資訊的調控模式。
結果:(1). XCSRtimetag分類時序生理訊號上在影片一與影片二正確率分別達98.74%以及 99.34%; (2). 重構訊號與原編碼訊號相減之差值訊號,統計分析結果顯示影片刺激事件中,兩組間表現顯著差異; (3). HIGD的差值訊號在主成分分析(Principal Components Analysis, PCA)之二維投影鏈結散佈圖上,在影片一與影片二表現出相反的變化; (4). 系統重構訊號之時間標籤分析中,HIGD在兩部影音刺激事件的時間資訊混用率呈現相反的變化。討論:HIGD在兩部負向情緒刺激的影片中出現相反的變化模態之可能原因,其中遊戲操作提示畫面出現次數在兩部影片差異較大,將其取代為刺激事件後分析,結果表示在特殊事件的刺激下,系統學習到HIGD會出現一致的調控變化。
總結而言,本研究將HIGD與LIGD觀看影片刺激時之呼吸資訊加以編碼、學習。XCSRtimetag學習結果顯示HIGD在對應特殊事件時呼吸變化與LIGD相比有不同的調控模式。
In the modern era of Internet popularity, Internet game addiction has gradually become a worry. In 2013, the American Psychiatric Association included Internet Gaming Disorder (IGD) to the list of recommending conditions for further research in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. Retrospective questionnaires such as the Young's Internet Addiction test and the Chen's Internet Addiction scale are mostly used clinically to assist clinical diagnosis. However, retrospective questionnaires with observation periods up to one year may be disadvantageous for immediate clinical diagnosis, except that tracking is not easy, and inhibition has the potential to produce memory confusion. Therefore, more objective physiological signaling modalities using computer analysis have been developed to indentify high-risk IGD (HIGD) and low-risk IGD (LIGD), among which the observation of respiratory regulatory mechanisms during gaming, especially the change in timing, is of particular interest.
To observe instantaneous changes in the timing of the HIGD and LIGD breathing patterns, we converted the respiratory signals to several respiratory information called analytic signal (AS), including Intrinsic Mode Function (IMF), instantaneous frequency (IF), and the ratio of IMF/IF via Ensemble Empirical Mode Decomposition and Normalized Direct Quadrature algorithm, which were encoded in sequence labeling problem. Dealing with the time series problem may encounter some problems due to the properties of time series, such as real numbers, noies, complexity, and the inability of the model to resolve states of the same individual at different times will result in decreased accuracy. Although traditional eXtended Learning Classifiers (eXtended Classifier System with real valued inputs, XCSR) has captured hunman-readable knowledge and interpretation architectures, they cannot disentangle temporal correlations between the state of the same individual at different times. Therefore, we introduce an XCSR with a time-tag (XCSRtimetag) to help the system learn time series problems by using the time-tag as a guide for the direction of classifier evolution. The reconsturction components were then used to reconstitute the signal to search for the pattern of regulation of the AS in HIGD and LIGD.
The results show that: (1) The accuracy of XCSRtimetag reaches to 98.74% and 99.34% in film1 and film2 respectively. (2) The statistical analysis results show that there is a significant difference between the two groups of the difference signal in the stimulus event. (3) The difference signal of HIGD shows opposite changes in the two-dimensional projection connected scatter of the principal component from film1 and film2. (4) The time-tag mixing rate of HIGD and LIGD's reconstructed signal also showed opposite changes during the stimulus events. Discussion: This study further discusses the possible reasons for the opposite analysis results of HIGD in the two negative emotional stimulus films. Among them, the game operation tips appear different in the number of times, and the result analyzed with game operation tips event shows that HIGD performed consistently in the two films, indicating that under the stimulation of special events, the system learned that HIGD would have similar regulatory changes.
In summary, this study encodes the respiratory information when HIGD and LIGD is watching the film stimulation. Our proposed method, XCSRtimetag can analyze time-series changes and explores the knowledge learned by the system which indicate that HIGD may have the same respiration regulation mode when dealing with special events in film stimulation.
摘要 I
英文摘要 III
目錄 V
表目錄 VII
圖目錄 VIII
英文縮寫 X
1. 緒論 1
1.1 研究背景 1
1.1.1網路遊戲成癮的定義與診斷 3
1.1.2網路遊戲成癮與生理訊號 5
1.2研究動機 7
1.3文獻探討 8
1.3.1觀察網路遊戲成癮者之生理訊號 8
1.3.2生理訊號之瞬時變化 10
1.3.3網路遊戲成癮與機器學習之應用 13
1.3.4可理解的機器學習-學習分類器 15
1.3.5 LCS之發展歷史 21
1.4研究目的 28
2. 實驗方法與分析方法 29
2.1實際呼吸資料集-實驗流程及設備 29
2.2分析訊號之轉換 32
2.2.1 總體經驗模態拆解法 32
2.2.2正規化正交演算法 34
2.3模擬訊號之設計與資料前處理 36
2.4 XCSR WITH TIME-TAG (XCSRTIMETAG) 39
2.5 重構訊號(RECONSTRUCTRED SIGNAL) 42
2.6系統重構訊號與呼吸分析訊號之差異 45
2.7 知識萃取 - 基於主成分分析的視覺化分析 46
2.8 統計分析 46
3. 結果 47
3.1 弦波模擬分析結果 47
3.2 實驗資料-呼吸訊號分析結果 51
3.2.1序列問題編碼 51
3.2.2 XCSRtimetag 分類結果 51
3.2.3重構訊號與差值訊號 53
3.2.4 統計分析 55
4. 研究討論 56
4.1 機器學習方法學之比較 56
4.2 分類器之解答空間分佈 –不同呼吸資訊之比較 57
4.3不同影片對於受測者之影響 61
4.4 主成分分析 62
4.5重建訊號之TIME-TAG分析 64
5. 結論 68
6. 未來工作 69
REFERENCE 70
簡歷 74
[1] Unity Technology. COVID-19’s Impact on the Gaming Industry: 19 Takeaways, 2020
[2] MASAELI, Nassim; FARHADI, Hadi. Prevalence of Internet-based addictive behaviors during COVID-19 pandemic: A systematic review. Journal of Addictive Diseases, 2021, 1-27.
[3] EDITION, Fifth. Diagnostic and statistical manual of mental disorders. American Psychiatric Association, 2013, 21.
[4] WORLD HEALTH ORGANIZATION. The International Statistical Classification of Diseases and Health Related Problems ICD-10: Tenth Revision. Volume 1: Tabular List. World Health Organization, 2004.
[5] YOUNG, Kimberly S. Caught in the net: How to recognize the signs of internet addiction--and a winning strategy for recovery. John Wiley & Sons, 1998.
[6] YOUNG, Kimberly S. Internet addiction: The emergence of a new clinical disorder. 2009.
[7] CHEN, Sue-Huei, et al. Development of a Chinese Internet addiction scale and its psychometric study. Chinese Journal of Psychology, 2003.
[8] ZHANG, Jialin, et al. Altered neural processing of negative stimuli in people with internet gaming disorder: fMRI evidence from the comparison with recreational game users. Journal of affective disorders, 2020, 264: 324-332.
[9] HONG, Sung Jun, et al. Altered heart rate variability during gameplay in internet gaming disorder: the impact of situations during the game. Frontiers in psychiatry, 2018, 9: 429.
[10] LI, Qi, et al. Dysfunctional cognitive control and reward processing in adolescents with Internet gaming disorder. Psychophysiology, 2020, 57.2: e13469.
[11] COYNE, Sarah M., et al. Physiological indicators of pathologic video game use in adolescence. Journal of Adolescent Health, 2015, 56.3: 307-313.
[12] HSIEH, Dai-Ling; HSIAO, Tzu-Chien. Heart rate variability of internet gaming disorder addicts in emotional states. In: 2016 International Conference on Biomedical Engineering (BME-HUST). IEEE, 2016. p. 155-158.
[13] JI, Hong-Ming; HSIAO, Tzu-Chien. Instantaneous Respiratory Response of Gamer with High-Risk Internet Gaming Disorder during Game-Film Stimuli by Using Complementary Ensemble Empirical Mode Decomposition. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2020. p. 980-983.
[14] CHANG, Jae Seung, et al. Altered cardiorespiratory coupling in young male adults with excessive online gaming. Biological psychology, 2015, 110: 159-166.
[15] JI, Hong-Ming; HSIAO, Tzu-Chien. A novel cue-induced abdominal reaction analysis for Internet gaming disorder. Journal of medical systems, 2019, 43.4: 1-8.
[16] YUAN, Kai, et al. Cortical thickness abnormalities in late adolescence with online gaming addiction. PloS one, 2013, 8.1: e53055.
[17] TERESHCHENKO, Sergey; KASPAROV, Edward. Neurobiological risk factors for the development of internet addiction in adolescents. Behavioral Sciences, 2019, 9.6: 62.
[18] YOUNG, Kimberly S.; BRAND, Matthias. Merging theoretical models and therapy approaches in the context of Internet gaming disorder: A personal perspective. Frontiers in psychology, 2017, 8: 1853.
[19] HONG, Soon-Beom, et al. Decreased functional brain connectivity in adolescents with internet addiction. PloS one, 2013, 8.2: e57831.
[20] PARK, Hyun Soo, et al. Altered regional cerebral glucose metabolism in internet game overusers: a 18F-fluorodeoxyglucose positron emission tomography study. CNS spectrums, 2010, 15.3: 159-166.
[21] KIM, Sang Hee, et al. Reduced striatal dopamine D2 receptors in people with Internet addiction. Neuroreport, 2011, 22.8: 407-411.
[22] LU, Dong Wei, et al. Differentiation of Internet addiction risk level based on autonomic nervous responses: the Internet-addiction hypothesis of autonomic activity. Cyberpsychology, Behavior, and Social Networking, 2010, 13.4: 371-378.
[23] JI, H.-M.; HSIEH, D.-L.; HSIAO, T.-C. Emotional responses of internet gaming disorder by doing abdominal breathing. In: 2016 International Conference on Biomedical Engineering (BME-HUST). IEEE, 2016. p. 150-154.
[24] HSIEH, Dai-Ling, et al. Respiratory feature extraction in emotion of internet addiction abusers using complementary ensemble empirical mode decomposition. Journal of Medical Imaging and Health Informatics, 2015, 5.2: 391-399.
[25] HUANG, Norden E., et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998, 454.1971: 903-995.
[26] WU, Zhaohua; HUANG, Norden E. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in adaptive data analysis, 2009, 1.01: 1-41.
[27] HUANG, Norden E., et al. On instantaneous frequency. Advances in adaptive data analysis, 2009, 1.02: 177-229.
[28] KIM, Hodam, et al. Detection of craving for gaming in adolescents with internet gaming disorder using multimodal biosignals. Sensors, 2018, 18.1: 102.
[29] JI, Hong-Ming; CHEN, Liang-Yu; HSIAO, Tzu-Chien. Real-time detection of internet addiction using reinforcement learning system. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2019. p. 1280-1288.
[30] HOLLAND, John H.; REITMAN, Judith S. Cognitive systems based on adaptive algorithms. In: Pattern-directed inference systems. Academic Press, 1978. p. 313-329.
[31] WILSON, Stewart W. Classifier fitness based on accuracy. Evolutionary computation, 1995, 3.2: 149-175.
[32] WILSON, Stewart W. Get real! XCS with continuous-valued inputs. In: International Workshop on Learning Classifier Systems. Springer, Berlin, Heidelberg, 1999. p. 209-219.
[33] HOLLAND, John H. Properties of the bucket brigade. Proceedings of the first international conference on genetic algorithms and their applications. Lawrence Erlbaum Associates, New York, 1985.
[34] WILSON, Stewart W. ZCS: A zeroth level classifier system. Evolutionary computation, 1994, 2.1: 1-18.
[35] WILSON, Stewart W. Function Approximation with a Classifier System. In: Proc. 3rd Genetic and Evolutionary Computation Conf.(GECCO’01)(p. 974À981). 2001.
[36] BULL, Larry; O'HARA, Toby. Accuracy-based neuro and neuro-fuzzy classifier systems. In: Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation. 2002. p. 905-911.
[37] BERNADÓ-MANSILLA, Ester; GARRELL-GUIU, Josep M. Accuracy-based learning classifier systems: models, analysis and applications to classification tasks. Evolutionary computation, 2003, 11.3: 209-238.
[38] TAMEE, Kreangsak; BULL, Larry; PINNGERN, Ouen. Towards clustering with XCS. In: Proceedings of the 9th annual conference on Genetic and evolutionary computation. 2007. p. 1854-1860.
[39] NAKATA, Masaya; KOVACS, Tim; TAKADAMA, Keiki. A modified XCS classifier system for sequence labeling. In: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation. 2014. p. 565-572.
[40] NAKATA, Masaya; KOVACS, Tim; TAKADAMA, Keiki. Messy Coding in the XCS Classifier System for Sequence Labeling. In: International Conference on Parallel Problem Solving from Nature. Springer, Cham, 2014. p. 191-200.
[41] CHEN, Liang-Yu; LEE, Po-Ming; HSIAO, Tzu-Chien. A Novel Representation of Classifier Conditions named sensory tag for the XCS in multistep problems. In: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation. 2015. p. 973-980.
[42] LAFFERTY, John; MCCALLUM, Andrew; PEREIRA, Fernando CN. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. 2001.
[43] LANZI, Pier Luca; WILSON, Stewart W. Toward optimal classifier system performance in non-Markov environments. Evolutionary Computation, 2000, 8.4: 393-418.
[44] WEBB, Andrew, et al. Controlling a simulated khepera with an xcs classifier system with memory. In: European Conference on Artificial Life. Springer, Berlin, Heidelberg, 2003. p. 885-892.
[45] KHARBAT, Faten; ODEH, Mohammed; BULL, Larry. New approach for extracting knowledge from the XCS learning classifier system. International Journal of Hybrid Intelligent Systems, 2007, 4.2: 49-62.
[46] DIXON, Philip W.; CORNE, David W.; OATES, Martin J. Encouraging compact rulesets from XCS for enhanced data mining. In: Applications of Learning Classifier Systems. Springer, Berlin, Heidelberg, 2004. p. 92-109.
[47] DIXON, Phillip William; CORNE, Dawid Wolfe; OATES, Martin John. A ruleset reduction algorithm for the XCS learning classifier system. In: International workshop on learning classifier systems. Springer, Berlin, Heidelberg, 2002. p. 20-29.
[48] WILSON, Stewart W. Compact rulesets from XCSI. In: International Workshop on Learning Classifier Systems. Springer, Berlin, Heidelberg, 2001. p. 197-208.
[49] TADOKORO, Masakazu, et al. Knowledge extraction from XCSR based on dimensionality reduction and deep generative models. In: 2019 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2019. p. 1883-1890.
[50] LIN, Jessica; KEOGH, Eamonn; LONARDI, Stefano. Visualizing and discovering non-trivial patterns in large time series databases. Information visualization, 2005, 4.2: 61-82.
[51] ALI, Mohammed, et al. TimeCluster: dimension reduction applied to temporal data for visual analytics. The Visual Computer, 2019, 35.6: 1013-1026.
[52] ALI, Mohammed, et al. Towards visual exploration of large temporal datasets. In: 2018 International Symposium on Big Data Visual and Immersive Analytics (BDVA). IEEE, 2018. p. 1-9.
[53] VAN DEN ELZEN, Stef, et al. Reducing snapshots to points: A visual analytics approach to dynamic network exploration. IEEE transactions on visualization and computer graphics, 2015, 22.1: 1-10.
[54] WELCH, Bernard L. The generalization of ‘STUDENT'S’problem when several different population varlances are involved. Biometrika, 1947, 34.1-2: 28-35.
[55] CHANG, Chih-Chung; LIN, Chih-Jen. LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2011, 2.3: 1-27.
[56] AMPOMAH, Ernest Kwame, et al. Stock Market Prediction with Gaussian Naïve Bayes Machine Learning Algorithm. Informatica, 2021, 45.2.
[57] WU, Mike, et al. Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database. Journal of the American Medical Informatics Association, 2017, 24.3: 488-495.
[58] KAMEL, Hajer; ABDULAH, Dhahir; AL-TUWAIJARI, Jamal M. Cancer classification using gaussian naive bayes algorithm. In: 2019 International Engineering Conference (IEC). IEEE, 2019. p. 165-170.
[59] GAYATHRI, B. M.; SUMATHI, C. P. An automated technique using Gaussian naïve Bayes classifier to classify breast cancer. International Journal of Computer Application, 2016, 148.6: 16-21.
[60] HOCHREITER, Sepp; SCHMIDHUBER, Jürgen. Long short-term memory. Neural computation, 1997, 9.8: 1735-1780.
[61] TSIOURIS, Κostas Μ, et al. A long short-term memory deep learning network for the prediction of epileptic seizures using EEG signals. Computers in biology and medicine, 2018, 99: 24-37.
[62] SINGH, Shraddha, et al. Classification of ECG arrhythmia using recurrent neural networks. Procedia computer science, 2018, 132: 1290-1297.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top