© 2015 The Authors Recently, bio-signal based control has been gradually deployed in biomedical devices and assistive robots for improving the quality of life of disabled and elderly people, among which electromyography (EMG) and electroencephalography (EEG) bio-signals are being used widely. This paper reviews the deployment of these bio-signals in the state of art of control systems. The main aim of this paper is to describe the techniques used for (i) collecting EMG and EEG signals and diving these signals into segments (data acquisition and data segmentation stage), (ii) dividing the important data and removing redundant data from the EMG and EEG segments (feature extraction stage), and (iii) identifying categories from the relevant data obtained in the previous stage (classification stage). Furthermore, this paper presents a summary of applications controlled through these two bio-signals and some research challenges in the creation of these control systems. Finally, a brief conclusion is summarized

This paper presents a user-friendly human machine interface (HMI) for hands-free control of an electric powered wheelchair (EPW). Its two operation modes are based on head movements: Mode 1 uses only one head movement to give the commands, and Mode 2 employs four head movements. An EEG device, namely Emotiv EPOC, has been deployed in this HMI to obtain the head movement information of users. The proposed HMI is compared with the joystick control of an EPW in an indoor environment. The experimental results show that Control Mode 2 can be implemented at a fast speed reliably, achieving a mean time of 67.90 seconds for the two subjects. However, Control Mode 1 has inferior performance, achieving a mean time of 153.20 seconds for the two subjects although it needs only one head movement. It is clear that the proposed HMI can be effectively used to replace the traditional joystick control for disabled and elderly people.

This systematic review aims to analyze the state-of-the-art regarding interaction modalities used on serious games for upper limb rehabilitation. A systematic search was performed in IEEE Xplore and Web of Science databases. PRISMA and QualSyst protocols were used to filter and assess the articles. Articles must meet the following inclusion criteria: they must be written in English; be at least four pages in length; use or develop serious games; focus on upper limb rehabilitation; and be published between 2007 and 2017. Of 121 articles initially retrieved, 33 articles met the inclusion criteria. Three interaction modalities were found: vision systems (42.4%), complementary vision systems (30.3%), and no-vision systems (27.2%). Vision systems and no-vision systems obtained a similar mean QualSyst (86%) followed by complementary vision systems (85.7%). Almost half of the studies used vision systems as the interaction modality (42.4%) and used the Kinect sensor to collect the body movements (48.48%). The shoulder was the most treated body part in the studies (19%). A key limitation of vision systems and complementary vision systems is that their device performances might be affected by lighting conditions. A main limitation of the no-vision systems is that the range-of-motion in angles of the body movement might not be measured accurately. Due to a limited number of studies, fruitful areas for further research could be the following: serious games focused on finger rehabilitation and trauma injuries, game difficulty adaptation based on user's muscle strength and posture, and multisensor data fusion on interaction modalities.

Medical conditions and accidents might cause immobility in certain parts of the body. In order to assist people in the rehabilitation process, sensors obtaining bio-signals from the body have been merged to create assistive technology. This systematic review is focused on presenting the state-ofthe- art regarding sensor fusion used in applications for hand rehabilitation. Articles were searched in four databases: IEEE Xplore, Web of science, ACM digital library and PubMed. Moreover, PRISMA and QualSyst protocols were employed to filter the articles and assess their qualities. As a result, of the 102 articles initially retrieved, only 29 articles performed sensor fusion for hand rehabilitation. Specifically, three application areas were found: sensor fusion for detecting hand movements, sensor fusion for exoskeleton control applications, and sensor fusion on serious games for hand rehabilitation. The studies included in this review measured two key aspects for rehabilitation purposes: user’s limb strength and user’s limb position. Regarding the sensors employed in the fusion, the most widely used sensor was electromyography sensor followed by inertial sensors. Furthermore, the studies included in this review have focused on the following hand movements used for rehabilitation: flexion, extension, pronation, supination, power grasp, radial/urnal, open hand, single-finger contractions, multi-finger contractions, pinch grip, hand at rest and hand grip.

An essential aspect in the interaction between people and computers is the recognition of facial expressions. A key issue in this process is to select relevant features to classify facial expressions accurately. This study examines the selection of optimal geometric features to classify six basic facial expressions: happiness, sadness, surprise, fear, anger, and disgust. Inspired by the Facial Action Coding System (FACS) and the Moving Picture Experts Group 4th standard (MPEG-4), an initial set of 89 features was proposed. These features are normalized distances and angles in 2D and 3D computed from 22 facial landmarks. To select a minimum set of features with the maximum classification accuracy, two selection methods and four classifiers were tested. The first selection method, principal component analysis (PCA), obtained 39 features. The second selection method, a genetic algorithm (GA), obtained 47 features. The experiments ran on the Bosphorus and UIVBFED data sets with 86.62% and 93.92% median accuracy, respectively. Our main finding is that the reduced feature set obtained by the GA is the smallest in comparison with other methods of comparable accuracy. This has implications in reducing the time of recognition.