Design and implementing wireless multimedia sensor network for movement detection using FPGA local co-processing

Varshovi, Hamzeh; Kavian, Yousef S.; Ansari-Asl, Karim

doi:10.1007/s11042-018-7104-0

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Varshovi et al address the problem of high volume of multimedia data in Wireless Multimedia Sensor Network (WMSN) by using the related processor for local image processing as a way to perform certain motion detection and send its related information to the base station The results show the effectiveness of the detection method. The results show that the detection effect using the method is better [10]. Yu et al In order to improve the stability of irregular tooth end mills, the radial cross section was designed parametrically, and the center coordinates of the end mill shape were calculated with the corresponding constructed mathematical model, and the spiral groove shape was optimized with the PSO algorithm.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Improved Particle Swarm Algorithm in Wireless Sensor Network Localization

Chen

2023

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

WSN localization occupies an important position in the practical application of WSN. To complete WSN localization efficiently and accurately, the article constructs the objective function based on the target node location constraints and maximum likelihood function. It avoids premature convergence through the PSO algorithm based on chaos search and backward learning. Based on linear fitting, the node-flipping fuzzy detection method is proposed to perform the judgment of node flipping fuzzy phenomenon. And the detection method is combined with the localization algorithm, and the final WSN localization algorithm is obtained after multi-threshold processing. After analysis, it is found that compared with other PSO algorithms, the MTLFPSO algorithm used in the paper has better performance with the highest accuracy of 83.1%. Different threshold values will affect the favorable and error detection rates of different WSNs. For type 1 WSNs, the positive detection rate of the 3-node network is the highest under the same threshold value, followed by the 4-node network; when the threshold value is 7.5 (3 ), the positive detection rate of the 3-node network is 97.8%. Different numbers of anchor nodes and communication radius will have specific effects on the number of definable nodes and relative localization error, in which the lowest relative localization error of the MTLFPSO algorithm is 3.4% under different numbers of anchor nodes; the lowest relative localization error of MTLFPSO algorithm is 2.5% under different communication radius. The article adopts the method to achieve accurate and efficient localization of WSNs.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In equation (10), i i i a g b < < . In the original search space, the fitness of each ( ) m g is calculated; Based on the calculated fitness, a more optimal solution * g is found and the value of this more optimal solution is assigned to gbest .…”

Section: Two-way Chaos Search-based Localization Algorithmmentioning

confidence: 99%