fast detection
Recently Published Documents


TOTAL DOCUMENTS

1100
(FIVE YEARS 342)

H-INDEX

44
(FIVE YEARS 11)

2022 ◽  
Vol 374 ◽  
pp. 131714
Author(s):  
Petar Ristivojević ◽  
Filip Andrić ◽  
Vesna Vasić ◽  
Dušanka Milojković Opsenica ◽  
Gertrud Morlock

2022 ◽  
pp. 101707
Author(s):  
Xinyue Li ◽  
Chunguang Wang ◽  
Zongshu Zhang ◽  
Chao Wang ◽  
Wenjing Wang ◽  
...  

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Wei-Feng Tung ◽  
Jaileez Jara Santiago Campos

PurposeSocial robot, a subtype of robots that is designed for the various interactive services for human, which must deliver superior user experience (UX) by expressing human-like social behavior or service and emotional sensitivity. This study develops a social robot app called the “Music Buddy” in ASUS Zenbo that provides a situational music based on the users' electroencephalogram (EEG) data. The research uses this app to explore its UX criteria and the prioritization of human robot interaction (HRI).Design/methodology/approachThe research methodologies include the both system development and decision analysis for the social robot. The first part is to design and develop a social robot app. The second part is to investigate the criteria of HRI through the Analytic Hierarchy Process (AHP) from UX aspects.FindingsIn view of the results of the AHP, the first-layer criteria consist of personalized function, easy-to-use the system and intelligent process. In terms of prioritization of multi-criteria, the overall ranking discloses the nine criteria in order including autonomy for robot, easy-to-use EEG device, accurate music preference, simple operations for brainwave device and easy-to-use applications, active music recommendation, automatic updates of music and easy-to-use robot as well as fast detection for emotion.Originality/valueThis research includes a self-developed social robot app and its UX research using AHP. This paper contributes to the improvement and innovation of the social robot design according to the results of UX research on HRI of social robot.


2021 ◽  
Author(s):  
Shihe Guo ◽  
Peisi Zhong ◽  
Yongpeng Sun ◽  
Liang Li ◽  
Chao Zhang

Author(s):  
Ibrahim I. Al-Naimi ◽  
Jasim A. Ghaeb ◽  
Mohammed J. Baniyounis ◽  
Mustafa Al-Khawaldeh

In this paper, the problem of voltage unbalance in the three-phase power systems is examined. A fast detection technique (FDT) is proposed to detect the voltage unbalance precisely and speedily. The well-known detection methods require more than one cycle time to detect the unbalanced voltages, whereas the proposed technique detects the unbalanced situations speedily in a discrete manner. Reducing the time duration required to detect the unbalanced voltages will enhance the dynamic response of the control system used to balance these voltages. The FDT acquires the instantaneous values of the three load voltages, calculates the sum and the space vector for these voltages at each sample, and utilizes these parameters to detect the voltage unbalance accurately within a quarter of the cycle time. A proof-of-concept simulation model for a real power system has been built. The parameters of the aqaba-qatrana-south amman (AQSA) Jordanian power system are considered in the simulation model. Also, several test cases have been conducted to test and validate the capabilities of the proposed technique.


Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7929
Author(s):  
Jianqiang Lu ◽  
Weize Lin ◽  
Pingfu Chen ◽  
Yubin Lan ◽  
Xiaoling Deng ◽  
...  

At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.


Sign in / Sign up

Export Citation Format

Share Document