Author(s)

Wei He

Affiliation(s)

School of Economics and Management, Minjiang University, Fuzhou, 350108, China.

Corresponding Author

Wei He, email: alvinhe@foxmail.com

ABSTRACT

This research proposes a Fuzzy C Means-based approach to identify moving vessels from a plethora of blips captured by radar. Initially, the graphical characteristics of radar blips in sequential radar frames, such as speed, course, and size, are quantified and selected as pieces of evidence in a Fuzzy C Means-based (FCM-based) model, which is used for identifying the authenticity of a blip being a real moving vessel. With the help of the FCM, it is feasible to build up an artificial intelligence to classify and identify the authenticities of radar blips, calculate the possibility of some blip being a real vessel based on the three pieces of evidence mentioned above. To archive the goals above, the chief problem of building a successful FCM framework is to find an appropriate way to offer a classification coefficient C and a fuzzy coefficient m. Since the C in classification is finite, this research proposes a method to obtain C by assessing the Euclidean distance of expected results. As the m is related to the discreteness of the evidence and results, this coefficient can be evaluated by Shannon Entropy and gain. In the field testing, the improved FCM was capable of classifying the radar blips accurately, lowering the working strength of ship operators, and improving the safety. A real case study has been conducted to validate the effectiveness and accuracy of the proposed approach. 

KEYWORDS

Marine Radar; Fuzzy C Means; Shannon Entropy; Fuzzy Inference.

CITE THIS PAPER

He Wei. A recognition approach of radar blips based on improved fuzzy C means. Journal of Computer Science and Electrical Engineering. 2019, 1(1): 26-33.

REFERENCES

[1]IALA Recommendation E-148, The need to implement regional e-navigation solutions based on international standards, Edition 1.0 December 2015.

[2]https://en.wikipedia.org/wiki/Vessel_traffic_service

[3]IALA Guideline No. 1103 on Train the Trainer Edition 1 December 2013

[4]IALA Guideline 1114 on A Technical Specification for the Common Shore-based System Architecture (CSSA) Edition 1.0 May 2015

[5]B. Lin & C.H. Huang: Comparison between ARPA radar and AIS characteristics for vessel traffic services [J]. Journal of Marine Science and Technology, Vol. 14, No. 3 (2006): 187-189.

[6]Ma Feng, etal. Error distinguish of AIS based on evidence combination [J]. Journal of Theoretical and Applied Information Technology, 2012, V.45(1): 83-90.

[7]Ma Feng, etal. Short message characteristics of AIS base stations [J]. Jiaotong Yunshu Gongcheng Xuebao/Journal of Traffic and Transportation Engineering, 2012, V.12(6):111-118

[8]Ma Feng, etal. The error distinguishing of automatic identification system based on improved evidence similarity // Proceddings of ICTIS: Improv. Multimodal Transp. Syst. - Inf., Saf., Integr. - Proc. Int. Conf. Transp. Inf. Saf. 2013: 715-722.

[9]Sang Lingzhi, etal. A quantificational description method of vessel track based on AIS data // Proceddings of ICTIS: Improv. Multimodal Transp. Syst. - Inf., Saf., Integr. - Proc. Int. Conf. Transp. Inf. Saf. 2013: 2358-2366.

[10]Liang Yulan, Lee John D. A hybrid Bayesian Network approach to detect driver cognitive distraction [J]. Transportation Research Part C: Emerging Technologies, 2014, V.38, p 146-155.

[11]Clark, Stephen D. Characterising and predicting car ownership using rough sets [J].Transportation Research Part C: Emerging Technologies, 2008, v.17(4): 381-393.

[12]Daneshfar Fatemeh, etal. Adaptive fuzzy urban traffic flow control using a cooperative multi-agent system based on two stage fuzzy clustering // Proceddings of Conference: VTC Spring 2009 - IEEE 69th Vehicular Technology, April, p 1 – 5.

[13]J. Wang, et al. A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints [J]. Computerized Medical Imaging and Graphics, V.32 (2008): 685-698.

[14]Santosh Kumar Nanda et al. Fuzzy-C-mean based radial basis function network application in machinery noise prediction [J]. Procedia Engineering, V.38 (2012): 3596-3602.

[15]A. Ghosh et al. Fuzzy clustering algorithms for unsupervised change detection in remote sensing images [J]. Information Sciences V.181 (2011): 699-715.

[16]Chatzis, S.P. et al. A fuzzy clustering approach toward hidden Markov random field models for enhanced spatially constrained image segmentation [J]. Fuzzy Systems, V.16 (2008): 1351-1361.

[17]Yang Li, Fusheng Yu. A new validity function for fuzzy clustering [C]// Proceedings of Computational Intelligence and Natural Computing International Conference. V.1 (2009): 462-465.

[18]Tai-Yu Ma, Jean-Patrick Lebacque. A cross entropy based multi-agent approach for multiclass activity chain modeling and simulation [J]. Transportation Research Part C V.28 (2013):116-129.

[19]James C. Bezdek, Robert Ehrlich, William Full. FCM: The fuzzy c-means clustering algorithm Original Research Article. Computers & Geosciences, V.10, Issues 2–3, 1984, Pages 191-203.

[20]Popescu, M, Bezdek, J.C. A cluster validity framework based on induced partition dissimilarity [J].  Cybernetics, IEEE Transactions.V.43. (2013):308 - 320.

[21]S.R. Kannan, S. Ramathilagam, P.C. Chung. Effective fuzzy c-means clustering algorithms for data clustering problems [J]. Expert Systems with Applications. Volume 39, Issue 7, 1 June 2012, Pages 6292–6300.

[22]Abonyi, J. et al. Modified Gath-Geva fuzzy clustering for identification of Takagi-Sugeno fuzzy models [J]. Systems, Man, and Cybernetics, Part B: Cybernetics, V.32, (2002):612 – 621.

[23]Hesam Izakiana , Ajith Abrahamb. Fuzzy C-means and fuzzy swarm for fuzzy clustering problem [J]. Expert Systems with Applications. Volume 38, Issue 3, March 2011, Pages 1835–1838

[24]Roberts, S.J.et al. Minimum-entropy data partitioning using reversible jump Markov chain Monte Carlo [J]. Pattern Analysis and Machine Intelligence. V.23 (2001): 909 - 914.

[25]Rui-Ping Li, et al. A maximum-entropy approach to fuzzy clustering [C]// Proceedings International Joint Conference of the Fourth IEEE International Conference, V.4 (1995):2227 - 2232.

[26]James C. Bezdek. Pattern Recognition with Fuzzy Objective Function Algorithms [Z]. 1981.

[27]Kwan Y. Chan, Richard H. Haschke. Epithelial-stromal interactions: Specific stimulation of corneal epithelial cell growth in vitro by a factor(s) from cultured stromal fibroblasts [J]. Experimental Eye Research. V.36, (1983): 231–246. 

[28]Pal, N.R. Bezdek, J.C. On cluster validity for the fuzzy c-means model Fuzzy Systems [J]. IEEE Transactions. V.3 (1995) 370 – 379 .