Going Green Using Combined Real-Time Analytics and Process Automation

2013 ◽  
pp. 255-320
Keyword(s):  
Real Time ◽  
Process Automation

scholarly journals Deep Robot-Human Interaction with Facial Emotion Recognition Using Gated Recurrent Units & Robotic Process Automation

2020 ◽  
Author(s):  
Suchitra Saxena ◽  
Shikha Tripathi ◽  
Sudarshan Tsb
Keyword(s):  
Emotion Recognition ◽  
Real Time ◽  
Research Work ◽  
Human Interaction ◽  
Facial Emotion Recognition ◽  
Facial Emotion ◽  
Process Automation ◽  
Training Time ◽  
Robotic Process Automation ◽  
Gated Recurrent Units

This research work proposes a Facial Emotion Recognition (FER) system using deep learning algorithm Gated Recurrent Units (GRUs) and Robotic Process Automation (RPA) for real time robotic applications. GRUs have been used in the proposed architecture to reduce training time and to capture temporal information. Most work reported in literature uses Convolution Neural Networks (CNN), Hybrid architecture of CNN with Long Short Term Memory (LSTM) and GRUs. In this work, GRUs are used for feature extraction from raw images and dense layers are used for classification. The performance of CNN, GRUs and LSTM are compared in the context of facial emotion recognition. The proposed FER system is implemented on Raspberry pi3 B+ and on Robotic Process Automation (RPA) using UiPath RPA tool for robot human interaction achieving 94.66% average accuracy in real time.

Novel Design of Heterogeneous Automation Controller Based on Real-Time Data Distribution Service Middleware to Avoid Obsolescence Challenges

2016 ◽  
Vol 25 (09) ◽  
pp. 1650111 ◽  
Author(s):  
Sadiq M. Sait ◽  
Ghalib A. Al-Hashim
Keyword(s):  
Real Time ◽  
Data Distribution ◽  
Partial Replacement ◽  
Limiting Factor ◽  
Input Output ◽  
Process Automation ◽  
Time Data ◽  
Automation Systems ◽  
Real Time Data ◽  
Data Distribution Service

Oil and gas processing facilities utilize various process automation systems with proprietary controllers. As the systems age; older technologies become obsolete resulting in frequent premature capital investments to sustain their operation. This paper presents a new design of automation controller to provide inherent mechanisms for upgrades and/or partial replacement of any obsolete components without obligation for a complete system replacement throughout the expected life cycle of the processing facilities. The input/output racks are physically and logically decoupled from the controller by converting them into distributed autonomous process interface systems. The proprietary input/output communication between the conventional controller CPU and the associated input/output racks is replaced with standard real-time data distribution service middleware for providing seamless cross-vendor interoperable communication between the controller and the distributed autonomous process interface systems. The objective of this change is to allow flexibility of supply for all controller’s subcomponents from multiple vendors to safeguard against premature automation obsolescence challenges. Detailed performance analysis was conducted to evaluate the viability of using the standard real-time data distribution service middleware technology in the design of automation controller to replace the proprietary input/output communication. The key simulation measurements to demonstrate its performance sustainability while growing in controller’s size based on the number of input/output signals are communication latency, variation in packets delays, and communication throughput. The overall performance results confirm the viability of the new proposal as the basis for designing cost effective evergreen process automation solutions that would result in optimum total cost of ownership capital investment throughout the systems’ life span. The only limiting factor is the selected network infrastructure.

Real-Time Cluster Resources Scheduling Strategy in WIA-PA Networks

2014 ◽  
Vol 989-994 ◽  
pp. 4253-4260 ◽  
Author(s):  
Yu Ping Sun ◽  
Ming Jie Fang ◽  
Jian Hua Sun
Keyword(s):  
Real Time ◽  
Edge Coloring ◽  
Industrial Process ◽  
Optimal Routing ◽  
Process Automation ◽  
Mesh Structure ◽  
Scheduling Strategy ◽  
Routing Mechanism ◽  
Automation Control ◽  
Hybrid Management

WIA-PA network is a kind of multi-hop wireless network, which is specially designed for industrial process automation control. It uses hybrid management pattern with star and mesh structure. Intra-cluster and inter-cluster communication is scheduled simultaneously based on TDMA as well as FDMA. In this paper, a real-time cluster resources scheduling strategy for WIA-PA networks is proposed and the specific algorithm is implemented by edge-coloring. Our algorithm combines with optimal routing mechanism and arranges the order of links reasonably, resulting in avoiding conflict and improving the original communication success rate. Furthermore, the algorithm makes full use of channel resources, which greatly reduces end-to-end delay. The performance analysis shows that our algorithm is close to optimal for WIA-PA networks. In addition, compared with RSCA algorithm, our algorithm has lower latency and higher network throughput.

Sign in / Sign up

Export Citation Format

Share Document