Hardware/Software Co-Design and VLSI Implementation for the Intelligent Surveillance System

Tsai, Tsung‐Han; Chang, Chih-Hao

doi:10.1109/jsen.2017.2732438

Cited by 9 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A basic structure of a MAS can be classified as a centralized architecture that can be created by a number of homogeneous or Non-communicating agents. This structure can be managed by a single console (master and slave) [53] such an arrangement closely reflects the traditional region [54]. Two specific classes of agents have been described: a set of agents that are equipped with increased intelligence and with a high-level communication capabilities.…”

Section: Summary Of An Intelligent Agentsmentioning

confidence: 99%

Intelligent Energy Management for Off-Grid Renewable Hybrid System Using Multi-Agent Approach

Sami

2020

IEEE Access

View full text Add to dashboard Cite

Smart Hybrid Home Power Systems are interested in studying power issues for isolated customers who have an off-grid power connection. The establishment of independent hybrid power systems has seen as a method of improving energy security. Our main goal is to ensure that energy is produced efficiently. To accomplish this objective, we have suggested a detailed simulation system in which the solar energy factor is considered as the main source. The system also incorporates energy storage devices to ensure safe energy distribution and recovery (Fuel Cell/Ultra-Capacitor). An Intelligent Energy Management System is developed and discussed to ensure that the system operates properly using a precise multi-agent system. The recommended power management system is designed to identify Multi-Agent tasks and to understand possible scenarios by the energy characteristics and energy demands. The reached results proved that the proposed system reaches the goals defined for Intelligent Energy Management System about an experimental database extracted from Tunisian climate services using Matlab/Simulink Software.

show abstract

Section: Summary Of An Intelligent Agentsmentioning

confidence: 99%

Intelligent Energy Management for Off-Grid Renewable Hybrid System Using Multi-Agent Approach

Sami

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The traditional labeling algorithm is very slow and requires much memory to store different parameters. While considering a real-time implementation, we use our previous work of [36], which is a combination of running length coding (RLC) and object labeling to perform the noise removal. This technique can reduce the computation time yet it maintains the performance of the system.…”

Section: B Labelingmentioning

confidence: 99%

Implementation of Fall Detection System Based on 3D Skeleton for Deep Learning Technique

Tsai

Hsu

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

In recent years, the fall detection system has become an important topic in the homecare system. Compared with the traditional fall detection algorithm, the method used by neural network is more robust and has higher accuracy. However neural network consumes a large amount of energy due to a huge number of computations, and needs more memory to store parameters as compared to traditional algorithms. In this paper, we propose a fall detection system in combination of the traditional algorithm with the neural network. First, we propose a skeleton information extraction algorithm, which transforms depth information into skeleton information and extracts the important joints related to fall activity. Also we have modified the skeleton-based method with seven highlight feature points. Second, we propose a highly robust deep convolution neural network architecture, which uses a pruning method to reduce parameters and calculations in the network. The low number of parameters and calculations makes the system suitable for the implementation on an embedded system. The experiment results show the high accuracy and robustness on the popular benchmark dataset NTU RGB+D. The proposed system has been implemented on NVIDIA Jetson Tx2 platform with real-time processing.

show abstract

Intelligent English Automatic Translation System Based on Multi-Feature Fusion

Wang

2022

2022 International Conference on Artificial Intelligence and Autonomous Robot Systems (AIARS)

View full text Add to dashboard Cite

Hardware/Software Co-Design and VLSI Implementation for the Intelligent Surveillance System

Cited by 9 publications

References 27 publications

Intelligent Energy Management for Off-Grid Renewable Hybrid System Using Multi-Agent Approach

Intelligent Energy Management for Off-Grid Renewable Hybrid System Using Multi-Agent Approach

Implementation of Fall Detection System Based on 3D Skeleton for Deep Learning Technique

Intelligent English Automatic Translation System Based on Multi-Feature Fusion

Contact Info

Product

Resources

About