Interface Identification of Automatic Verification System Based on Deep Learning

Author(s):  
Andi Zheng ◽  
Yaqiong Fu ◽  
Mingze Dong ◽  
Xinyi Du ◽  
Yueming Chen ◽  
...  
Author(s):  
Yunfei Guo ◽  
Wenda Xu ◽  
Sarthak Pradhan ◽  
Cesar Bravo ◽  
Pinhas Ben-Tzvi

Abstract Efficient human-machine interface (HMI) for exoskeletons remains an active research topic, where sample methods have been proposed including using computer vision, EEG (electroencephalogram), and voice recognition. However, some of these methods lack sufficient accuracy, security, and portability. This paper proposes a HMI referred as integrated trigger-word configurable voice activation and speaker verification system (CVASV). The CVASV system is designed for embedded systems with limited computing power that can be applied to any exoskeleton platform. The CVASV system consists of two main sections, including an API based voice activation section and a deep learning based text-independent voice verification section. These two sections are combined into a system that allows the user to configure the activation trigger-word and verify the user’s command in real-time.


2019 ◽  
Vol 3 (2) ◽  
Author(s):  
Qian Li ◽  
Jian Wang ◽  
Xiaotian Ma ◽  
Yi Wang ◽  
Yonglu Han

Abstract: In the process of metering and automatic production system in the measurement and verification of the loading robot, if there is a positional shift of the electric meter, the gripper of the loading robot will mechanically collide with the electric meter. Due to the large force of the loading robot, the appearance of the electric meter is damaged, and the mechanical arm of the loading robot is broken, which reduces the service life of the measuring and verifying equipment, which is not conducive to the continuous and stable operation of the automatic verification system. In this paper, an automatic detection system of electric meter position in the turnaround box is proposed, which can reduce the failure rate of the automatic verification system, improve the verification efficiency, reduce the loss of metering assets and the occurrence of safety accidents by realizing the offset detection and correction of the electric meter position in the turnover box.


Sign in / Sign up

Export Citation Format

Share Document