0018-9294 (c) 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TBME.2018.2834555, IEEE Transactions on Biomedical Engineering IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1 An EOG-based Human Machine Interface to Control a Smart Home Environment for Patients with Severe Spinal Cord Injuries Rui Zhang † , Shenghong He † , Xinghua Yang, Xiaoyun Wang, Kai Li, Qiyun Huang, Zhenghui Gu, Zhuliang Yu, Xichun Zhang, Dan Tang * and Yuanqing Li * Abstract—Objective: This paper presents an asynchronous EOG-based human machine interface (HMI) for smart home environmental control with the purpose of providing daily as- sistance for severe spinal cord injury (SCI) patients. Methods: The proposed HMI allows users to interact with a smart home environment through eye blinking. Specifically, several buttons, each corresponding to a control command, randomly flash on a graphical user interface. Each flash of the buttons functions as a visual cue for the user to blink. To issue a control command, the user can blink synchronously with the flashes of the corre- sponding button. Through detecting blinks based on the recorded EOG signal, the target button and its corresponding control command are determined. Seven SCI patients participated in an online experiment, during which the patients were required to control a smart home environment including household electrical appliances, an intelligent wheelchair as well as a nursing bed via the proposed HMI. Results: The average false operation ratio in the control state was 4.1%, whereas during the idle state, no false operations occurred. Conclusion: All SCI patients were able to control the smart home environment using the proposed EOG-based HMI with satisfactory performance in terms of the false operation ratio in both the control and the idle states. Significance: The proposed HMI offers a simple and effective approach for patients with severe SCIs to control a smart home environment. Therefore, it is promising to assist severe SCI patients in their daily lives. Index Terms—Human-machine interface (HMI), electrooculog- raphy (EOG), environmental control, spinal cord injury (SCI). This work was supported by the National Key Basic Research Program of China (973 Program) under Grant 2015CB351703, the National Natural Sci- ence Foundation of China under Grants 61633010, 91420302 and 61703101, and Guangdong Natural Science Foundation under Grant 2014A030312005. Asterisk indicates corresponding author. R. Zhang is with the School of Electrical Engineering & Intelligentization, Dongguan University of Technology, with the School of Automation Science and Engineering, South China University of Technology, and also with the Guangzhou Key Laboratory of Brain Computer Interface and Applications. S. He, K. Li, Q. Huang, Z. Gu, Z. Yu, X. Zhang and *Y. Li are with the School of Automation Science and Engineering, South China University of Technology, and also with the Guangzhou Key Laboratory of Brain Computer Interface and Applications, Guangzhou, 510640, China (correspondence e- mail: auyqli@scut.edu.cn). X. Yang, X. Wang, *D. Tang are with Guangdong Provincial Work Injury Rehabilitation Hospital, Guangzhou, 510440, China (correspondence e-mail: tangdan8@163.com). †These authors contributed equally to this work. Copyright (c) 2017 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending an email to pubs-permissions@ieee.org. I. I NTRODUCTION Millions of people around the world suffer from severe neuromuscular disorders, such as spinal cord injuries (SCIs), multiple sclerosis (MS) or strokes. These severely paralyzed patients cannot convey their intentions to external devices via conventional human machine interfaces (HMIs) such as joysticks, keyboards or mouses [1]. Therefore, it is necessary to develop alternative HMIs for these patients to restore their ability to control the external environment. Recently, the research and development of HMIs based on biological signals, particularly electroencephalography (EEG)- and electrooculography (EOG)-based HMIs, have shown great potential to address this challenge because they are non- invasive, inexpensive and convenient [2]. EEG-based HMIs are also referred to as brain computer interfaces (BCIs). The EEG patterns that are widely employed to develop BCI systems include motor imagery (MI) [3], [4], P300 potentials [5]–[7], steady-state visual evoked potentials (SSVEPs) [8], motion- onset visual evoked potentials (mVEPs) [9] and their hybrid patterns [10]–[14]. Compared with MI-based BCIs, SSVEP-, mVEP- and P300-based BCIs are more widely used because they require minimal training and have high accuracy and sta- ble performance [15]–[17]. It is reported that the flicker stimuli associated with SSVEP-based BCIs may cause annoyance and fatigue for some users, especially for elderly subjects and paralyzed patients [18]. Contrary to SSVEP-based BCIs, P300 and mVEP-based BCIs can reduce fatigue and discomfort in subjects because they do not require strong visual stimulus [14]. However, most EEG-based BCIs suffer from high false positive rates while the subject is in an idle state due to unstable and noisy EEG signals [19]. BCIs are especially suitable for the patients suffering from severe motor disabilities, such as the patients with total locked- in syndrome (LIS), who have little or no residual motor ability [20]. Some paralyzed patients, such as most of the SCI patients, often retain normal vision and the ability to control their eye movements. This residual ability can be used to develop EOG-based HMIs. In recent years, various EOG- based HMI systems have been developed for environmental control [21]–[25]. For instance, Barea et al. developed an EOG-based HMI for wheelchair control based on four eye- gaze directions, i.e., up/down/left/right gaze [21]. Lled´ o et al. proposed an EOG-based internet browser, in which eye- gaze directions and blinks were employed to move the mouse