Showing papers by "Charles W. Anderson published in 2017"
University of Michigan1, Northern Michigan University2, Technical University of Berlin3, Auckland University of Technology4, University of Freiburg5, Starlab6, Brown University7, Graz University of Technology8, University of Paris9, Utrecht University10, University of Twente11, New York State Department of Health12, United States Army Research Laboratory13, École Polytechnique Fédérale de Lausanne14, University of Bremen15, Cornell University16, University of California, Irvine17, United States Department of Veterans Affairs18, Carnegie Mellon University19, University of Oldenburg20, University of Pittsburgh21, Colorado State University22
TL;DR: The Sixth International Brain–Computer Interface Meeting was held 30 May–3 June 2016 at the Asilomar Conference Grounds, Pacific Grove, California, USA and included 28 workshops covering topics in BCI and brain–machine interface research.
Abstract: The Sixth International Brain–Computer Interface (BCI) Meeting was held 30 May–3 June 2016 at the Asilomar Conference Grounds, Pacific Grove, California, USA. The conference included 28 workshops covering topics in BCI and brain–machine interface research. Topics included BCI for specific populations or applications, advancing BCI research through use of specific signals or technological advances, and translational and commercial issues to bring both implanted and non-invasive BCIs to market. BCI research is growing and expanding in the breadth of its applications, the depth of knowledge it can produce, and the practical benefit it can provide both for those with physical impairments and the general public. Here we provide summaries of each workshop, illustrating the breadth and depth of BCI research and highlighting important issues and calls for action to support future research and development.
24 citations
TL;DR: This article demonstrates the ongoing work that utilizes word clustering when conducting Arabic sentiment analysis by combining the clustering feature with sentiment analysis for Arabic and improved the performance of the classifier.
Abstract: Rich morphology language, such as Arabic, requires more investigation and methods targeted toward improving the sentiment analysis task. An example of external knowledge that may provide some semantic relationships within the text is the word clustering technique. This article demonstrates the ongoing work that utilizes word clustering when conducting Arabic sentiment analysis. Our proposed method employs supervised sentiment classification by enriching the feature space model with word cluster information. In addition, the experiments and evaluations that were conducted in this study demonstrated that by combining the clustering feature with sentiment analysis for Arabic, this improved the performance of the classifier.
8 citations
19 Dec 2017
TL;DR: The results provide evidence of capability of the Emotiv EPOC+ headset to detect the P300 signals from two channels, O1 and O2 and show that longer flash duration resulted in larger P300 amplitude and the effect of using colored matrix was clear on the O2 channel.
Abstract: 12 Objective: The P300 signal is an electroencephalography (EEG) positive deflection observed 300 ms to 600 ms after an infrequent, but expected, stimulus is presented to a subject. The aim of this study was to investigate the capability of Emotiv EPOC+ headset to capture and record the P300 wave. Moreover, the effects of using different matrix sizes, flash duration, and colors were studied. Methods: Participants attended to one cell of either 6x6 or 3x3 matrix while the rows and columns flashed randomly at different duration (100 ms or 175 ms). The EEG signals were sent wirelessly to OpenViBE software, which is used to run the P300 speller. Results: The results provide evidence of capability of the Emotiv EPOC+ headset to detect the P300 signals from two channels, O1 and O2. In addition, when the matrix size increases, the P300 amplitude increases. The results also show that longer flash duration resulted in larger P300 amplitude. Also, the effect of using colored matrix was clear on the O2 channel. Furthermore, results show that participants reached accuracy above 70% after three to four training sessions. Conclusion: The results confirmed the capability of the Emotiv EPOC+ headset for detecting P300 signals. In addition, matrix size, flash duration, and colors can affect the P300 speller performance. Significance: Such an affordable and portable headset could be utilized to control P300-based BCI or other BCI systems especially for the out-of-the-lab applications. 13
3 citations
14 May 2017
TL;DR: This research develops a novel learning approach that acquires important samples from practice and then applies them to a target RL task without changing learned bases, and shows an improved learning efficiency through practice in classical benchmark problems and limitations in OpenAI Gym problems.
Abstract: A reinforcement learning (RL) agent needs a fair amount of experience to find a near-optimal policy. Transfer learning has been investigated as a means to reduce the amount of experience required. Transfer learning, however, requires another similar reinforcement learning task as a transfer source, which can also be costly in the amount of experience required. In this research, we examine the possible “practice” approach that transfers knowledge from a non-RL task to a target RL task to avoid the expensive data sampling. We analyze how practice captures the distributions of state and action spaces in an environment. For this, we develop a novel learning approach that acquires important samples from practice and then applies them to a target RL task without changing learned bases. Results show an improved learning efficiency through practice in classical benchmark problems and limitations in OpenAI Gym problems.
2 citations