一個腦波資訊管理系統架構雛形

在台灣排隊是一個非常普遍的現象，幾乎每個人都有過排隊的體驗，在一個列隊中，等待的空間、氣味、周圍的聲音，或前後排隊人數，都會影響消費者是否願意排隊。然而所有的因素都會影響到大腦，透過分析大腦數據來行銷是一種趨勢。所謂最好的行銷是透過分析工具找到策略，因此生理訊號的大數據分析是值得研究的，但目前沒有基於行銷目的而發明的腦波資訊系統。基於這個目的，本研究使用先前學者收集的大量腦波資料，設計了一套腦波資訊系統雛形。本研究透過資料探勘進行循序樣式資料探勘找尋消費者會排隊與不會排隊的腦波規則，再將資料透過K-means分群，最後使用隨機森林建立出準確的分類模型，並採用ETL方法設置了一個資料倉儲系統。本研究應用統一軟體開發過程原則來建構系統，使系統符合使用者需求。最後，本研究使用單通道腦波儀進行實驗收集腦波資料，來驗證系統建構之腦波資料的準確度。

關鍵字

腦波；排隊；資料探勘；雛形系統

並列摘要

Queuing for services is a common situation in Taiwan. The environment, sound, or queuing size affects customer willingness to queue. Restated, brain decided to queue or not. How to find the correlation between brainwave and queuing decision is worthy the study for marketing. However, no brainwave system is invented for this matter. Therefore, this study designed a prototype information system for analyzing brainwave. This study applied data mining technology, random forest and cluster analysis, on finding the rules. Finally, this study also built up a data warehouse system and the prototype system through Rational Unified Process (RUP). The brainwave experiment has made for evaluating the performance of the system.

並列關鍵字

Brainwave ； Queuing ； Data mining ； Prototype system

參考文獻

Liang, C.C., Kuo, F.Y. (2018). Decision on Queue-A Study of Cognitive and Brainwave Responses. Chinese Journal of Psychology, 60(3), 191-215. doi: 10.6129/CJP.201809_60(3).0003

Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29. doi: 10.1145/1007730.1007735

Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. doi: 10.1023/A:1010933404324

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357. doi: 10.1613/jair.953

Chen, J., Hu, B., Moore, P., Zhang, X., & Ma, X. (2015). Electroencephalogram-based emotion assessment system using ontology and data mining techniques. Applied Soft Computing, 30, 663-674. doi: 10.1016/j.asoc.2015.01.007

主題瀏覽