In this paper, a multi-tag optimization method based on image analysis and particle swarm optimization (PSO) neural network is proposed to verify the effect of radio frequency identification (RFID) multi-tag distribution on the performance of the system. A RFID tag detection system is proposed with two charge coupled device (CCD). This system can automatically focus on the tag according to its position, so it can obtain the image information more accurately by template matching and edge detection method. Therefore, the spatial structure of multi-tag and the corresponding reading distance can be obtained for training. Because of its excellent performance in multi-objective optimization, the PSO neural network is used to train and predict multi-tag distribution at the maximum reading distance. Compared with other neural networks, PSO is more accurate and its uptime is shorter for RFID multi-tag analysis.
Abdel-AzizYIKararaHMHauckM (2015) Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. Photogrammetric Engineering & Remote Sensing81(2): 103–107.
2.
AsadiEda SilvaMGAntunesCHet al. (2014) Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an application. Energy and Buildings81: 444–456.
De ReuJDe SmedtPHerremansDet al. (2014) On introducing an image-based 3D reconstruction method in archaeological excavation practice. Journal of Archaeological Science41: 251–262.
5.
DengDJTsaoHW (2011) Optimal dynamic framed slotted ALOHA based anti-collision algorithm for RFID systems. Wireless Personal Communications59(1): 109–122.
6.
EbrahimiEMonjeziMKhalesiMRArmaghaniDJ (2016) Prediction and optimization of back-break and rock fragmentation using an artificial neural network and a bee colony algorithm. Bulletin of Engineering Geology and the Environment75(1): 27–36.
7.
GandinoFFerreroRMontrucchioBRebaudengoM (2011) Probabilistic DCS: An RFID reader-to-reader anti-collision protocol. Journal of Network and Computer Applications34(3): 821–832.
8.
GoulartJTBassaniRABassaniJWM (2017) Application based on the Canny edge detection algorithm for recording contractions of isolated cardiac myocytes. Computers in Biology and Medicine81: 106–110.
9.
HamtaNGhomiSFJolaiFShiraziMA (2013) A hybrid PSO algorithm for a multi-objective assembly line balancing problem with flexible operation times, sequence-dependent setup times and learning effect. International Journal of Production Economics141(1): 99–111.
10.
HansenLKSalamonP (1990) Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence12(10): 993–1001.
11.
HenryPKraininMHerbstEet al. (2010) RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments. The International Journal of Robotics Research31(5): 647–663.
12.
KhannaVDasBKBishtDSinghPK (2015) A three diode model for industrial solar cells and estimation of solar cell parameters using PSO algorithm. Renewable Energy78: 105–113.
13.
LiZLiJHeCet al. (2015) RFID reader-to-reader collision avoidance model with multiple-density tag distribution solved by artificial immune network optimization. Applied Soft Computing30: 249–264.
14.
LiuZGuanZShangKet al. (2014) Continuous detection anti-collision algorithm for EPC Gen2 RFID systems. In:The Proceedings of the Second International Conference on Communications, Signal Processing, and Systems, pp. 1127–1136. Cham: Springer.
15.
PluhacekMSenkerikRDavendraDet al. (2013) On the behavior and performance of chaos driven PSO algorithm with inertia weight. Computers & Mathematics with Applications66(2): 122–134.
16.
SedghiMAliakbar-GolkarMHaghifamMR (2013) Distribution network expansion considering distributed generation and storage units using modified PSO algorithm. International Journal of Electrical Power & Energy Systems52: 221–230.
17.
SinghSDatarA (2015) Improved hash based approach for secure color image steganography using canny edge detection method. International Journal of Computer Science and Network Security (IJCSNS)15(7): 92–98.
18.
SungWTChungHY (2014) A distributed energy monitoring network system based on data fusion via improved PSO. Measurement55: 362–374.
19.
TsanakasJAChrysostomouDBotsarisPNGasteratosA (2015). Fault diagnosis of photovoltaic modules through image processing and Canny edge detection on field thermographic measurements. International Journal of Sustainable Energy34(6): 351–372.
20.
WangJKatabiD Dude (2013) Where’s my card? RFID positioning that works with multipath and non-line of sight. ACM SIGCOMM Computer Communication Review43(4): 51–62.
21.
YangPWuWMoniriMChibelushiCC (2013) Efficient object localization using sparsely distributed passive RFID tags. IEEE Transactions on Industrial Electronics60(12): 5914–5924.
22.
YooJHwangSSKimSDet al. (2014) Scale-invariant template matching using histogram of dominant gradients. Pattern Recognition47(9): 3006–3018.
23.
YuYYuXZhaoZet al. (2016a) Measurement uncertainty limit analysis of biased estimators in RFID multiple tags system. IET Science, Measurement & Technology10(5): 449–455.
24.
YuYSZhouYJZhaoZMet al. (2016b) Method for detecting optimal distribution of RFID multiple tags based on Fisher matrix. Journal of Xidian University43(2): 108–113.
25.
ZuoJMShahABKimHet al. (2014) Lattice and strain analysis of atomic resolution Z-contrast images based on template matching. Ultramicroscopy136: 50–60.
