Abstract
In recent times, the control of human-computer interface (HCI) systems is triggered by electrooculography (EOG) signals. Eye movements recognized based on the EOG signal pattern are utilized to govern the HCI system and do a specific job based on the type of eye movement. With the knowledge of various related examinations, this paper intends a novel model for eye movement recognition based on EOG signals by utilizing Grey Wolf Optimization (GWO) with neural network (NN). Here, the GWO is used to minimize the error function from the classifier. The performance of the proposed methodology was investigated by comparing the developed model with conventional methods. The results reveal the loftier performance of the adopted method with the error minimization analysis and recognition performance analysis in correspondence with varied performance measures such as accuracy, sensitivity, specificity, precision, false-positive rate (FPR), false-negative rate (FNR), negative predictive value (NPV), false discovery rate (FDR) and the F1 score.
Author statement
Research funding: Authors state no funding involved.
Conflict of interest: Authors state no conflict of interest.
Informed consent: Informed consent is not applicable.
Ethical approval: The conducted research is not related to either human or animal use.
References
[1] Wu L, Liao LD, Lu SW, Jiang WL, Chen SA, Lin CT. Controlling a human–computer interface system with a novel classification method that uses electrooculography signals. IEEE Trans Biomed Eng 2013;60:2133–41.10.1109/TBME.2013.2248154Search in Google Scholar PubMed
[2] Hosseinifarda B, Moradia MH, Rostamib R. Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal. Comput Methods Programs Biomed 2013;109:339–45.10.1016/j.cmpb.2012.10.008Search in Google Scholar PubMed
[3] Johns MW, Tucker A, Chapman RJ, Crowley KE, Michael N. Monitoring eye and eyelid movements by infrared reflectance oculography to measure drowsiness in drivers. Somnologie 2007;11:234–42.10.1007/s11818-007-0311-ySearch in Google Scholar
[4] Kocha H, Christensena JAE, Frandsenb R, Zoetmuldere M, Arvastsonc L, Christensenc SR, et al. Automatic sleep classification using a data-driven topic model reveals latent sleep states. J Neurosci Methods 2014;235:130–7.10.1016/j.jneumeth.2014.07.002Search in Google Scholar PubMed
[5] Rienzo MD, Rizzo F, Parati G, Brambilla G, Ferratini M, Castiglioni P. MagIC system: a new textile-based wearable device for biological signal monitoring. Applicability in Daily Life and Clinical Setting, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, 2005;7:71679.Search in Google Scholar
[6] Lee S, Yan L, Roh T, Hong S, and Yoo HJ. A 75\mu W real-time scalable body area network controller and a 25\mu W ExG Sensor IC for Compact Sleep Monitoring Applications. IEEE J Solid-State Circ 2012;47:323–34.10.1109/JSSC.2011.2170636Search in Google Scholar
[7] Rezazadeha IM, Wangb X, Firoozabadia M, Golpayegani MRH. Using affective human–machine interface to increase the operation performance in virtual construction crane training system: a novel approach. Autom Construct 2011;20:289–98.10.1016/j.autcon.2010.10.005Search in Google Scholar
[8] Law CKH, Leung MYY, Xu Y, Tso SK. A cap as interface for wheelchair control, IEEE/RSJ International Conference on Intelligent Robots and Systems 2002;2:1439–44.Search in Google Scholar
[9] Nam Y, Koo B, Cichocki A, and Choi S. GOM-Face: GKP, EOG, and EMG-based multimodal interface with application to humanoid robot control. IEEE Trans Biomed Eng 2014;61:453–62.10.1109/TBME.2013.2280900Search in Google Scholar PubMed
[10] Minati L, Yoshimura N, Koike Y. Hybrid control of a vision-guided robot arm by EOG, EMG, EEG biosignals and head movement acquired via a consumer-grade wearable device. IEEE Access 2016;4:9528–41.10.1109/ACCESS.2017.2647851Search in Google Scholar
[11] Wang G, Teng C, Li K, Zhang Z, Yan X. The removal of EOG artifacts from EEG signals using independent component analysis and multivariate empirical mode decomposition. IEEE J Biomed Health Informat 2016;20:1301–8.10.1109/JBHI.2015.2450196Search in Google Scholar PubMed
[12] Maddirala AK, Shaik RA. Removal of EOG artifacts from single channel EEG signals using combined singular spectrum analysis and adaptive noise canceler. IEEE Sensors J 2016;16:8279–87.10.1109/JSEN.2016.2560219Search in Google Scholar
[13] Morettia DV, Babilonia F, Carduccia F, Cincottia F, Remondinia E, Rossinib PM, et al. Computerized processing of EEG–EOG–EMG artifacts for multi-centric studies in EEG oscillations and event-related potentials. Int J Psychophysiol 2003;47:199–216.10.1016/S0167-8760(02)00153-8Search in Google Scholar PubMed
[14] Willigenburg NW, Daffertshofer A, Kingma I, Dieen JH. Removing ECG contamination from EMG recordings: a comparison of ICA-based and other filtering procedures. J Electromyogr Kinesiol 2012;22:485–93.10.1016/j.jelekin.2012.01.001Search in Google Scholar PubMed
[15] Gomez-Gil J, Gonzalez SJ, Nicolas-Alonso LF, Alonso-Garcia S. Steering a tractor by means of an EMG-based human-machine interface. Sensors (Basel) 2011;11:7110–26.10.3390/s110707110Search in Google Scholar PubMed PubMed Central
[16] Rezazadeh IM, Firoozabadi SM, Hu H, Golpayegani SMH. A novel human--machine interface based on recognition of multi-channel facial bioelectric signals. Australasian Physical Eng Sci Med 2011;34:497–513.10.1007/s13246-011-0113-1Search in Google Scholar PubMed
[17] Kim KK, Lim YK, Park KS. Common mode noise cancellation for electrically non-contact ECG measurement system on a chair. In: 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2005;6:5881–3.Search in Google Scholar
[18] Barea R, Boquete L, Rodriguez-Ascariz JM, Ortega S, LopezE. Sensory system for implementing a human-computer interface based on electrooculography. Sensors (Basel) 2011;11:310–28.10.3390/s110100310Search in Google Scholar PubMed PubMed Central
[19] Deng LY, Hsu CL, Lin TC, Tuan JS, Chang SM. EOG-based human-computer interface system development. Expert Syst Appl 2010;37:3337–43.10.1016/j.eswa.2009.10.017Search in Google Scholar
[20] Dhillon HS, Singla R, Rekhi NS, Jha R. EOG and EMG based virtual keyboard: a brain-computer interface. In: 2nd IEEE International Conference on Computer Science and Information Technology 2009;25962.10.1109/ICCSIT.2009.5234951Search in Google Scholar
[21] Barea R, Boquete L, Mazo M, Lpez E. Wheelchair guidance strategies using EOG. J Intelligent Robotic Syst 2002;34: 279–99.10.1023/A:1016359503796Search in Google Scholar
[22] Subasi A, Ercelebi E. Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 2005;78:87–99.10.1016/j.cmpb.2004.10.009Search in Google Scholar PubMed
[23] Wang S, Zhang Y, Ji G, Yang J, Wu J, Wei L. Fruit classification by Wavelet-Entropy and feedforward neural network trained by fitness-scaled chaotic ABC and biogeography-based optimization 2015;17:5711–28.10.3390/e17085711Search in Google Scholar
[24] Wang S, Zhang Y, Dong Z, Du S, Ji G, Yan J, et al. Feed-forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection. 2015;25:153–64.10.1002/ima.22132Search in Google Scholar
[25] Christensen JAE, Zoetmulder M, Koch H, Frandsen R, Arvastson L, Christensen SR, et al. Data-driven modeling of sleep EEG and EOG reveals characteristics indicative of pre-Parkinson’s and Parkinson’s disease. J Neurosci Methods 2014;235:262–76.10.1016/j.jneumeth.2014.07.014Search in Google Scholar PubMed
[26] Paul GM, Cao F, Torah R, Yang K, Beeby S, Tudor J. A smart textile based facial EMG and EOG computer interface. IEEE Sensors J 2014;14:393–400.10.1109/JSEN.2013.2283424Search in Google Scholar
[27] Manabe H, Fukumoto M, Yagi T. Direct gaze estimation based on nonlinearity of EOG. IEEE Trans Biomed Eng 2015;62:1553–62.10.1109/TBME.2015.2394409Search in Google Scholar PubMed
[28] Liang SF, Kuo CE, Lee YC, Lin WC, Liu YC, Chen PY, et al. Development of an EOG-based automatic sleep-monitoring eye mask. IEEE Transactions on Instrumentation and Measurement 2015;64:2977–85.10.1109/TIM.2015.2433652Search in Google Scholar
[29] Pavu KS, Thomas V. An algorithm for accelerating GHM Multiwavelet transformation on FPGA. 2012 International Conference on Data Science & Engineering (ICDSE), Cochin, Kerala 2012;1237.10.1109/ICDSE.2012.6282308Search in Google Scholar
[30] Mirjalilia S, Mirjalilib SM, Lewisa A. Grey Wolf optimizer. Adv Eng Software 2014;69:46–61.10.1016/j.advengsoft.2013.12.007Search in Google Scholar
[31] Toledo A, Pinzolas M, Ibarrola JJ, Lera G. Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient. IEEE Transactions on Neural Networks 2005;16:988–92.10.1109/TNN.2005.849849Search in Google Scholar PubMed
[32] Celika O, Tekeb A, Yildirima HB. The optimized artificial neural network model with Levenberg–Marquardt algorithm for global solar radiation estimation in Eastern Mediterranean Region of Turkey. J Cleaner Product 2016;116:1–12.10.1016/j.jclepro.2015.12.082Search in Google Scholar
©2020 Walter de Gruyter GmbH, Berlin/Boston
