Real-time EEG-based Affective Computing Using On-chip Learning Long-term Recurrent Convolutional Network

Author(s):  
Cheng-Jie Yang ◽  
Wei-Chih Li ◽  
Meng-Teen Wan ◽  
Wai-Chi Fang
2018 ◽  
Vol 81 (1) ◽  
pp. e62 ◽  
Author(s):  
Eyal Karzbrun ◽  
Rami Yair Tshuva ◽  
Orly Reiner
Keyword(s):  

Molecules ◽  
2019 ◽  
Vol 24 (4) ◽  
pp. 675 ◽  
Author(s):  
Yi Zhao ◽  
Ranjith Kankala ◽  
Shi-Bin Wang ◽  
Ai-Zheng Chen

With advantageous features such as minimizing the cost, time, and sample size requirements, organ-on-a-chip (OOC) systems have garnered enormous interest from researchers for their ability for real-time monitoring of physical parameters by mimicking the in vivo microenvironment and the precise responses of xenobiotics, i.e., drug efficacy and toxicity over conventional two-dimensional (2D) and three-dimensional (3D) cell cultures, as well as animal models. Recent advancements of OOC systems have evidenced the fabrication of ‘multi-organ-on-chip’ (MOC) models, which connect separated organ chambers together to resemble an ideal pharmacokinetic and pharmacodynamic (PK-PD) model for monitoring the complex interactions between multiple organs and the resultant dynamic responses of multiple organs to pharmaceutical compounds. Numerous varieties of MOC systems have been proposed, mainly focusing on the construction of these multi-organ models, while there are only few studies on how to realize continual, automated, and stable testing, which still remains a significant challenge in the development process of MOCs. Herein, this review emphasizes the recent advancements in realizing long-term testing of MOCs to promote their capability for real-time monitoring of multi-organ interactions and chronic cellular reactions more accurately and steadily over the available chip models. Efforts in this field are still ongoing for better performance in the assessment of preclinical attributes for a new chemical entity. Further, we give a brief overview on the various biomedical applications of long-term testing in MOCs, including several proposed applications and their potential utilization in the future. Finally, we summarize with perspectives.


2013 ◽  
Vol 2013 ◽  
pp. 1-17 ◽  
Author(s):  
Kais Loukil ◽  
Nader Ben Amor ◽  
Mohamed Abid ◽  
Jean Philippe Diguet

The emergence of mobile and battery operated multimedia systems and the diversity of supported applications mount new challenges in terms of design efficiency of these systems which must provide a maximum application quality of service (QoS) in the presence of a dynamically varying environment. These optimization problems cannot be entirely solved at design time and some efficiency gains can be obtained at run-time by means of self-adaptivity. In this paper, we propose a new cross-layer hardware (HW)/software (SW) adaptation solution for embedded mobile systems. It supports application QoS under real-time and lifetime constraints via coordinated adaptation in the hardware, operating system (OS), and application layers. Our method relies on an original middleware solution used on both global and local managers. The global manager (GM) handles large, long-term variations whereas the local manager (LM) is used to guarantee real-time constraints. The GM acts in three layers whereas the LM acts in application and OS layers only. The main role of GM is to select the best configuration for each application to meet the constraints of the system and respect the preferences of the user. The proposed approach has been applied to a 3D graphics application and successfully implemented on an Altera FPGA.


Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4597
Author(s):  
Zi-Xuan Yu ◽  
Meng-Shi Li ◽  
Yi-Peng Xu ◽  
Sheraz Aslam ◽  
Yuan-Kang Li

The optimal planning of grid-connected microgrids (MGs) has been extensively studied in recent years. While most of the previous studies have used fixed or time-of-use (TOU) prices for the optimal sizing of MGs, this work introduces real-time pricing (RTP) for implementing a demand response (DR) program according to the national grid prices of Iran. In addition to the long-term planning of MG, the day-ahead operation of MG is also analyzed to get a better understanding of the DR program for daily electricity dispatch. For this purpose, four different days corresponding to the four seasons are selected for further analysis. In addition, various impacts of the proposed DR program on the MG planning results, including sizing and best configuration, net present cost (NPC) and cost of energy (COE), and emission generation by the utility grid, are investigated. The optimization results show that the implementation of the DR program has a positive impact on the technical, economic, and environmental aspects of MG. The NPC and COE are reduced by about USD 3700 and USD 0.0025/kWh, respectively. The component size is also reduced, resulting in a reduction in the initial cost. Carbon emissions are also reduced by 185 kg/year.


2021 ◽  
Author(s):  
Intissar Khalifa ◽  
Ridha Ejbali ◽  
Raimondo Schettini ◽  
Mourad Zaied

Abstract Affective computing is a key research topic in artificial intelligence which is applied to psychology and machines. It consists of the estimation and measurement of human emotions. A person’s body language is one of the most significant sources of information during job interview, and it reflects a deep psychological state that is often missing from other data sources. In our work, we combine two tasks of pose estimation and emotion classification for emotional body gesture recognition to propose a deep multi-stage architecture that is able to deal with both tasks. Our deep pose decoding method detects and tracks the candidate’s skeleton in a video using a combination of depthwise convolutional network and detection-based method for 2D pose reconstruction. Moreover, we propose a representation technique based on the superposition of skeletons to generate for each video sequence a single image synthesizing the different poses of the subject. We call this image: ‘history pose image’, and it is used as input to the convolutional neural network model based on the Visual Geometry Group architecture. We demonstrate the effectiveness of our method in comparison with other methods in the state of the art on the standard Common Object in Context keypoint dataset and Face and Body gesture video database.


Sign in / Sign up

Export Citation Format

Share Document