Software is a critical component of brain–computer interfaces (BCIs). While BCI hardware enables the retrieval of brain signals, BCI software is required to analyze these signals, produce output, and provide feedback. Users from multiple research areas have adopted BCI software platforms to investigate various concepts. Recently, interest in web-based BCI software has also emerged. The system design and control signal techniques of state-of-the-art BCI software platforms have been previously investigated. However, there is limited literature discussing user adoption of BCI software platforms. Additionally, there is a lack of work discussing the recent emergence of web tools relevant to BCI applications. This article aims to address these gaps by presenting a bibliometric review of the state-of-the-art BCI software. Furthermore, we discuss web-based BCIs and present tools that may be used to develop future web-based BCI applications.

Purpose of Review: To discuss the current state of reproducibility of research in human-robot interaction (HRI), challenges specific to the field, and recommendations for how the community can support reproducibility. Recent Findings: As in related fields such as artificial intelligence, robotics, and psychology, improving research reproducibility is key to the maturation of the body of scientific knowledge in the field of HRI. The ACM/IEEE International Conference on Human-Robot Interaction introduced a theme on Reproducibility of HRI to their technical program in 2020 to solicit papers presenting reproductions of prior research or artifacts supporting research reproducibility. Summary: This review provides an introduction to the topic of research reproducibility for HRI and describes the state of the art in relation to the HRI 2020 Reproducibility theme. As a highly interdisciplinary field that involves work with technological artifacts, there are unique challenges to reproducibility in HRI. Biases in research evaluation and practice contribute to challenges in supporting reproducibility, and the training of researchers could be changed to encourage research reproduction. The authors propose a number of solutions for addressing these challenges that can serve as guidelines for the HRI community and related fields.

The past decade has seen great advancements in speech recognition for control of interactive devices, personal assistants, and computer interfaces. However, deaf and hard-of-hearing (HoH) individuals, whose primary mode of communication is sign language, cannot use voice-controlled interfaces. Although there has been significant work in video-based sign language recognition, video is not effective in the dark and has raised privacy concerns in the deaf community when used in the context of human ambient intelligence. RF sensors have been recently proposed as a new modality that can be effective under the circumstances where video is not. This article considers the problem of recognizing a trigger sign (wake word) in the context of daily living, where gross motor activities are interwoven with signing sequences. The proposed approach exploits multiple RF data domain representations (time-frequency, range-Doppler, and range-angle) for sequential classification of mixed motion data streams. The recognition accuracy of signs with varying kinematic properties is compared and used to make recommendations on appropriate trigger sign selection for RF-sensor-based user interfaces. The proposed approach achieves a trigger sign detection rate of 98.9% and a classification accuracy of 92% for 15 ASL words and three gross motor activities.

RF sensors have been recently proposed as a new modality for sign language processing technology. They are noncontact, effective in the dark, and acquire a direct measurement of signing kinematic via exploitation of the micro-Doppler effect. First, this work provides an in depth comparative examination of the kinematic properties of signing as measured by RF sensors for both fluent ASL users and hearing imitation signers. Second, as ASL recognition techniques utilizing deep learning requires a large amount of training data, this work examines the effect of signing kinematics and subject fluency on adversarial learning techniques for data synthesis. The following two different approaches for the synthetic training data generation are proposed: 1) adversarial domain adaptation to minimize the differences between imitation signing and fluent signing data and 2) kinematically-constrained generative adversarial networks for accurate synthesis of RF signing signatures. The results show that the kinematic discrepancies between imitation signing and fluent signing are so significant that training on data directly synthesized from fluent RF signers offers greater performance (93% top-5 accuracy) than that produced by adaptation of imitation signing (88% top-5 accuracy) when classifying 100 ASL signs.

Deaf spaces are unique indoor environments designed to optimize visual communication and Deaf cultural expression. However, much of the technological research geared towards the deaf involve use of video or wearables for American sign language (ASL) translation, with little consideration for Deaf perspective on privacy and usability of the technology. In contrast to video, RF sensors offer the avenue for ambient ASL recognition while also preserving privacy for Deaf signers. Methods: This paper investigates the RF transmit waveform parameters required for effective measurement of ASL signs and their effect on word-level classification accuracy attained with transfer learning and convolutional autoencoders (CAE). A multi-frequency fusion network is proposed to exploit data from all sensors in an RF sensor network and improve the recognition accuracy of fluent ASL signing. Results: For fluent signers, CAEs yield a 20-sign classification accuracy of %76 at 77 GHz and %73 at 24 GHz, while at X-band (10 Ghz) accuracy drops to 67%. For hearing imitation signers, signs are more separable, resulting in a 96% accuracy with CAEs. Further, fluent ASL recognition accuracy is significantly increased with use of the multi-frequency fusion network, which boosts the 20-sign fluent ASL recognition accuracy to 95%, surpassing conventional feature level fusion by 12%. Implications: Signing involves finer spatiotemporal dynamics than typical hand gestures, and thus requires interrogation with a transmit waveform that has a rapid succession of pulses and high bandwidth. Millimeter wave RF frequencies also yield greater accuracy due to the increased Doppler spread of the radar backscatter. Comparative analysis of articulation dynamics also shows that imitation signing is not representative of fluent signing, and not effective in pre-training networks for fluent ASL classification. Deep neural networks employing multi-frequency fusion capture both shared, as well as sensor-specific features and thus offer significant performance gains in comparison to using a single sensor or feature-level fusion.

This literature review explores prior research involving physiological-based mobile educational systems. Mobile computing is advancing, and implementations of ubiquitous systems for educational purposes are increasing. Another growing field is physiological computing, where the user's states are retrieved and applied as control inputs in applications. The integration of physiological signals such as electroencephalography (EEG), heart rate (ECG/EKG), and eye-tracking (EOG) to mobile learning (m-learning) applications can enhance the learning experiences to provide content tailored to the student's and educator's preferences. This article centers around a selection of core papers that represent the most relevant contributions to the research that falls at the intersection of m-learning and physiological computing. Specifically, this article presents an analysis and discussion of state-of-the-art mobile educational systems that leverage physiological technology.