注意力不集中往往會造成日常的麻煩和影響到工作績效，因此本研究提出基於單通道腦波訊號的注意力判別架構，在客觀情境以及主觀感受下都能有不錯的準確度。

方法:
(1) 30位受試者參與實驗並且全程皆戴者腦波儀以便記錄，實驗有兩種任務狀態:休息和測驗，在測驗結束後會要求受試者寫一份自我評估量表。
(2) 提取單通道(Fp1)腦波之時域、頻域、非線性特徵作為特徵集候選組，並以後向遞迴特徵選擇法選出局部最佳特徵集合。
(3) 採用支持向量機(Support Vector Machine, SVM) 作為注意力判別的分類器。
(4) 以移動平均濾波器對模型預測結果進行平滑校正。

分析結果:
(1) 根據客觀實驗設置和主觀的自我評估量表建立客觀模型和主觀模型，並且準確度分別是86%和82%。
(2) 為了模擬日常情況下注意力缺失，混合兩種任務狀態的腦波建立混和模型，準確度70%以上。
(3)探討不同頻帶上的平均功率在主觀模型和客觀模型下的相關性，發現Alpha、Beta、DTR、TBR在主客觀有相同的趨勢。

關鍵字:單通道腦電圖，主客觀注意力判別，機器學習

Inattention often causes daily troubles and affects work performance. Therefore, this research proposes an attention recognition architecture based on the single-channel Electroencephalography (EEG), which can have good accuracy in both objective situations and subjective feelings.

Method:
(1) Thirty subjects participated in the experiment and they wore a brainwave device for recording throughout the experiment. The experiment had two task states: rest and test. After the test, the subjects were asked to write a self-assessment report.
(2) Extract the time-domain, frequency-domain, and nonlinear features of single-channel (Fp1) EEG as the feature set candidate group, and then select the local best feature set by the backward recursive feature selection method.
(3) Adopt Support Vector Machine (SVM) as the classifier for attention recognition.
(4) Smooth and correct the model prediction results with a moving average filter.

Analysis Result:
(1) Establish objective model and subjective model based on objective experimental settings and subjective self-assessment report, and the accuracy is 86% and 82%, respectively.
(2) In order to simulate the lack of attention in daily situations, establish the mixed model by mixing the EEG signals of the two task states and the mixed model has the accuracy more than 70%.
(3) Explore the average power in different frequency bands on the subjective model and the objective model, and find the same trends in Alpha，Beta，DTR and TBR frequency bands between subjective and objective attention recognition .

Keywords: Single-channel EEG, Subjective and objective attention recognition, Machine learning

[1] Posner, Michael I., and Steven E. Petersen. "The attention system of the human brain." Annual review of neuroscience 13.1 (1990): 25-42.
[2] Sturm, Walter, and Klaus Willmes. "On the functional neuroanatomy of intrinsic and phasic alertness." Neuroimage 14.1 (2001): S76-S84.
[3] Nagai, Y., et al. "Brain activity relating to the contingent negative variation: an fMRI investigation." Neuroimage 21.4 (2004): 1232-1241.
[4] Corbetta, Maurizio, and Gordon L. Shulman. "Control of goal-directed and stimulus-driven attention in the brain." Nature reviews neuroscience 3.3 (2002): 201-215.
[5] Corbetta, Maurizio, et al. "A common network of functional areas for attention and eye movements." Neuron 21.4 (1998): 761-773.
[6] Wright, Richard D., and Lawrence M. Ward. Orienting of attention. Oxford University Press, 2008.
[7] Carter, Cameron S., and Marie K. Krug. "Dynamic cognitive control and frontal-cingulate interactions." Cognitive neuroscience of attention 2 (2012): 89-98.
[8] Botvinick, Matthew M., et al. "Conflict monitoring and cognitive control." Psychological review 108.3 (2001): 624.
[9] Bush, George, Phan Luu, and Michael I. Posner. "Cognitive and emotional influences in anterior cingulate cortex." Trends in cognitive sciences 4.6 (2000): 215-222.
[10] Watson, David, and Lee Anna Clark. "The PANAS-X: Manual for the positive and negative affect schedule-expanded form." (1999).
[11] Crawford, John R., and Julie D. Henry. "The Positive and Negative Affect Schedule (PANAS): Construct validity, measurement properties and normative data in a large non‐clinical sample." British journal of clinical psychology 43.3 (2004): 245-265.
[12] Silverthorn, Dee Unglaub, Johnson, Bruce R, Ober, William C, Garrison, Claire W, & Silverthorn, Andrew C. (2016). Human physiology : an integrated approach (Seventh edition.). Pearson.
[13] Webster, John G., ed. Medical instrumentation: application and design. John Wiley & Sons, 2009.
[14] Schomer, Donald L., and Fernando Lopes Da Silva. Niedermeyer's electroencephalography: basic principles, clinical applications, and related fields. Lippincott Williams & Wilkins, 2012.
[15] Jasper, H.. “Report of the committee on methods of clinical examination in electroencephalography.” Electroencephalography and Clinical Neurophysiology 10 (1958): 370-375.
[16] Nomenclature, Standard Electrode Position. "American electroencephalographic society guidelines for." Journal of clinical Neurophysiology 8.2 (1991): 200-2.
[17]李颖洁, 邱意弘, 朱贻盛, 脑电信号分析方法及其应用, 2 編者, 北京: 科学出版社, 2009.
[18] Kaplan, A. Ia. "The nonstability of the EEG: a methodological and experimental analysis." Uspekhi fiziologicheskikh nauk 29.3 (1998): 35-55.
[19] Stroop, J. Ridley. "Studies of interference in serial verbal reactions." Journal of experimental psychology 18.6 (1935): 643.
[20] MacLeod, Colin M. "Half a century of research on the Stroop effect: an integrative review." Psychological bulletin 109.2 (1991): 163.
[21] MacLeod, Colin M., and Penny A. MacDonald. "Interdimensional interference in the Stroop effect: Uncovering the cognitive and neural anatomy of attention." Trends in cognitive sciences 4.10 (2000): 383-391.
[22] Power, Sarah D., Tiago H. Falk, and Tom Chau. "Classification of prefrontal activity due to mental arithmetic and music imagery using hidden Markov models and frequency domain near-infrared spectroscopy." Journal of neural engineering 7.2 (2010): 026002.
[23] Watson, David, and Lee Anna Clark. "The PANAS-X: Manual for the positive and negative affect schedule-expanded form." (1999).
[24] Widmann, Andreas, Erich Schröger, and Burkhard Maess. "Digital filter design for electrophysiological data–a practical approach." Journal of neuroscience methods 250 (2015): 34-46.
[25] Ghaderi, Foad, Hamid R. Mohseni, and Saeid Sanei. "Localizing heart sounds in respiratory signals using singular spectrum analysis." IEEE Transactions on Biomedical Engineering 58.12 (2011): 3360-3367.
[26] Sadasivan, P. K., and D. Narayana Dutt. "SVD based technique for noise reduction in electroencephalographic signals." Signal Processing 55.2 (1996): 179-189.
[27] Teixeira, Ana R., et al. "Automatic removal of high-amplitude artefacts from single-channel electroencephalograms." Computer methods and programs in biomedicine 83.2 (2006): 125-138.
[28] Maddirala, Ajay Kumar, and Rafi Ahamed Shaik. "Removal of EOG artifacts from single channel EEG signals using combined singular spectrum analysis and adaptive noise canceler." IEEE Sensors Journal 16.23 (2016): 8279-8287.
[29] Gómez-Herrero, Germán, et al. "Automatic removal of ocular artifacts in the EEG without an EOG reference channel." Proceedings of the 7th Nordic Signal Processing Symposium-NORSIG 2006. IEEE, 2006.
[30] Aliakbaryhosseinabadi, Susan, et al. "Classification of EEG signals to identify variations in attention during motor task execution." Journal of neuroscience methods 284 (2017): 27-34.
[31] Murugappan, M., Subbulakshmi Murugappan, and Celestin Gerard. "Wireless EEG signals based neuromarketing system using Fast Fourier Transform (FFT)." 2014 IEEE 10th international colloquium on signal processing and its applications. IEEE, 2014.
[32] Welch, Peter. "The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms." IEEE Transactions on audio and electroacoustics 15.2 (1967): 70-73.
[33] Smith, J.O. "Hamming Window", in Spectral Audio Signal Processing,
http://ccrma.stanford.edu/~jos/sasp/Hamming_Window.html, online book,
2011 edition,
[34] Richman, Joshua S., and J. Randall Moorman. "Physiological time-series analysis using approximate entropy and sample entropy." American Journal of Physiology-Heart and Circulatory Physiology (2000).
[35] Goldberger, Ary L., et al. "Fractal dynamics in physiology: alterations with disease and aging." Proceedings of the national academy of sciences 99.suppl 1 (2002): 2466-2472.
[36] Hjorth, Bo. "EEG analysis based on time domain properties." Electroencephalography and clinical neurophysiology 29.3 (1970): 306-310.
[37] Krakovská, Anna, and Kristína Mezeiová. "Automatic sleep scoring: A search for an optimal combination of measures." Artificial intelligence in medicine 53.1 (2011): 25-33.
[38] Alex, Allwin, et al. "EEG analysis of brain activity in attention deficit hyperactivity disorder during an attention task." 2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI). IEEE, 2017.
[39] Guyon, Isabelle, et al. "Gene selection for cancer classification using support vector machines." Machine learning 46.1 (2002): 389-422.
[40] Cortes, Corinna, and Vladimir Vapnik. "Support-vector networks." Machine learning 20.3 (1995): 273-297.
[41] Liu, Yinxia, et al. "Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG." IEEE transactions on neural systems and rehabilitation engineering 20.6 (2012): 749-755.
[42] Dockree, Paul M., et al. "Optimal sustained attention is linked to the spectral content of background EEG activity: greater ongoing tonic alpha (∼ 10 Hz) power supports successful phasic goal activation." European Journal of Neuroscience 25.3 (2007): 900-907.
[43] Putman, Peter, et al. "EEG theta/beta ratio as a potential biomarker for attentional control and resilience against deleterious effects of stress on attention." Cognitive, Affective, & Behavioral Neuroscience 14.2 (2014): 782-791.
[44] Barry, Robert J., Adam R. Clarke, and Stuart J. Johnstone. "A review of electrophysiology in attention-deficit/hyperactivity disorder: I. Qualitative and quantitative electroencephalography." Clinical neurophysiology 114.2 (2003): 171-183.
[45] Loo, Sandra K., and Scott Makeig. "Clinical utility of EEG in attention-deficit/hyperactivity disorder: a research update." Neurotherapeutics 9.3 (2012): 569-587.
[46] Aminov, Anna, et al. "Acute single channel EEG predictors of cognitive function after stroke." PloS one 12.10 (2017): e0185841.
[47] Liu, Ning-Han, Cheng-Yu Chiang, and Hsuan-Chin Chu. "Recognizing the degree of human attention using EEG signals from mobile sensors." sensors 13.8 (2013): 10273-10286.
[48] Mohamed, Zainab, et al. "Characterizing focused attention and working memory using EEG." Sensors 18.11 (2018): 3743.
[49] Hu, Bin, et al. "Attention recognition in EEG-based affective learning research using CFS+ KNN algorithm." IEEE/ACM transactions on computational biology and bioinformatics 15.1 (2016): 38-45.
[50] Djamal, Esmeralda C., Dewi P. Pangestu, and Dea A. Dewi. "EEG-based recognition of attention state using wavelet and support vector machine." 2016 International Seminar on Intelligent Technology and Its Applications (ISITIA). IEEE, 2016.
[51] Acı, Çiğdem İnan, Murat Kaya, and Yuriy Mishchenko. "Distinguishing mental attention states of humans via an EEG-based passive BCI using machine learning methods." Expert Systems with Applications 134 (2019): 153-166.
[52] Myrden, Andrew, and Tom Chau. "A passive EEG-BCI for single-trial detection of changes in mental state." IEEE Transactions on neural systems and rehabilitation Engineering 25.4 (2017): 345-356.
[53] Ke, Yufeng, et al. "Visual attention recognition based on nonlinear dynamical parameters of EEG." Bio-medical materials and engineering 24.1 (2014): 349-355.