基于半监督模糊聚类算法的奶牛行为判别系统

doi:10.16431/j.cnki.1671-7236.2018.11.017

摘要/Abstract

摘要：

以实时判别奶牛行为，提升精细养殖技术水平为目标，本试验以系统功耗低、检测灵敏度高、运行稳定性强为原则设计无线传感节点，研发了一种基于半监督模糊聚类算法的奶牛行为实时判别系统。为获取最佳通信距离及最优节点固定高度，对无线传感节点分别进行固定高度—通讯距离与丢包率关系测试、固定高度—数据波动关系测试，通信距离分别取10、20、30 m，固定高度分别取10、20、30 cm；并将半监督模糊聚类判别算法、K-means算法及BP神经网络算法在奶牛行为识别方面的准确度、精度及敏感度进行比较。结果显示，集成三轴加速度传感器ADXL345、处理器MSP430-F149、无线收发器CC1101等芯片设计的无线传感节点可精确采集奶牛运动加速度数据，满足长期可靠传输数据等工作要求。固定高度—通讯距离与丢包率、固定高度—数据波动关系测试结果显示，最优传输距离为10 m，最佳节点固定高度为30 cm。半监督模糊聚类算法性能最高，平均准确度达到95.4%，平均精度为53.0%，平均敏感度为60.6%。K-means算法的平均准确度达到90.3%，平均精度仅有39.9%，平均敏感度为45.6%。BP神经网络算法平均准确度达到93.7%，平均精度为45.5%，平均敏感度为47.0%。半监督模糊聚类算法具有准确性高、学习复杂度低、运行速度快的特点，具有良好的寻优能力，效率较高。

关键词: 奶牛运动行为; 实时判别; 无线传感节点; 半监督模糊聚类算法

Abstract:

In order to determine the behavior of cows and improve the management level of fine feed,a Real-time identification system for cows' movement behaviors based on the semi-supervised fuzzy clustering algorithm was developed and the wireless sensor node was designed on the principle of low power consumption,high sensitivity and high operational stability.At the same time,the transmission performance of wireless sensor nodes was tested to determine the optimal transmission distance and the optimal node fixed height,in which the transmission distance were set at 10,20 and 30 m,while the fixed height were 10,20 and 30 cm,respectively.And the accuracy,precision and sensitivity of K-means algorithm,BP neural networks algorithm and semi-supervised fuzzy clustering algorithm were compared.The results showed that the wireless sensor node consist with three-axis accelerometer ADXL345,processor MSP430-F149,and wireless transceiver CC1101 which could collect data automatically of cows' movement behaviors,and meet the long-term reliable data transmission and other work requirements.The test results showed that the optimal transmission distance was 10 m and the optimal fixed node height was 30 cm.The accuracy,precision and sensitivity of semi-supervised fuzzy clustering algorithm were 95.4%,53.0% and 60.6%,respectively,that of K-means algorithm,BP neural network were 90.3%,39.9%,45.6% and 93.7%,45.5%,47.0%,respectively.In conclusion,the accuracy of semi-supervised fuzzy clustering algorithm was high,implementation was simple,learning complexity was low and running speed was fast,and it also had strong optimization ability.

Key words: cow behavior; Real-time discriminant; wireless sensor node; semi-supervisory fuzzy clustering algorithm

中图分类号:

TP274.2

王俊, 谭骥, 张海洋, 赵凯旋. 基于半监督模糊聚类算法的奶牛行为判别系统[J]. 《中国畜牧兽医》, 2018, 45(11): 3112-3121.

WANG Jun, TAN Ji, ZHANG Haiyang, ZHAO Kaixuan. A Cow Behavior Classification System Based on Semi-supervised Fuzzy Clustering Algorithm[J]. , 2018, 45(11): 3112-3121.

参考文献

[1] 杨晋辉,郑楠,杨永新,等.红外光谱在牛奶生产和检测方面的研究进展[J].农业工程学报,2016,32(17):1-11. YANG J H,ZHENG N,YANG Y X,et al.Research advances in milk production and detection by infrared spectroscopy[J].Transaction of the Chinese Society of Agricultural Engineering,2016,32(17):1-11.(in Chinese)
[2] 顾静秋,王志海,高荣华,等.基于融合图像与运动量的奶牛行为识别方法[J].农业机械学报,2017,48(6):145-151. GU J Q,WANG Z H,GAO R H,et al.Recognition method of cow behavior based on combination of image and activities[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(6):145-151.(in Chinese)
[3] 沈维政,郑爽,初永良,等.基于ADXL345的奶牛活动量采集系统设计[J].东北农业大学学报,2014,45(10):80-85. SHEN W Z,ZHENG S,CHU Y L,et al.Design of cow activity data acquisition system based on ADXL345[J].Journal of Northeast Agricultural University,2014,45(10):80-85.(in Chinese)
[4] 张建华,赵璞,刘佳佳,等.物联网在奶牛养殖中的应用及展望[J].农业展望,2014,10(10):51-56. ZHANG J H,ZHAO P,LIU J J,et al.Application situation and outlook of internet of things in dairy farming[J].Agricultural Outlook,2014,10(10):51-56.(in Chinese)
[5] 赵明礼,张珅,郝海生,等.同期发情和同期排卵-定时输精技术在奶牛繁殖中的应用[J].中国畜牧杂志,2015,51(17):80-86. ZHAO M L,ZHANG K,HAO H S,et al.Application of estrus synchronization and ovsynch-timed artificial insemination in dairy cattle[J].Chinese Journal of Animal Science,2015,51(17):80-86.(in Chinese)
[6] 熊本海,杨振刚,杨亮,等.中国畜牧业物联网技术应用研究进展[J].农业工程学报,2015,31(s1):237-246. XIONG B H,YANG Z G,YANG L,et al.Review on application of internet of things technology in animal husbandry in China[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(s1):237-246.(in Chinese)
[7] NADIMI E S,SØGAARD H T,BAK T.ZigBee-based wireless sensor networks for classifying the behavior of a herd of animals using classification trees[J].Biosystems Engineering,2008,100(2):167-176.
[8] SWARTZ T H,MCGILLIARD M L,PETERSSONWOLFE C S.Technical note:The use of an accelerometer for measuring step activity and lying behaviors in dairy calves[J].Journal of Dairy Science,2016,99(11):9109-9113.
[9] KAMPHUIS C,DELARUE B,BURKE C R,et al.Field evaluation of 2 collar-mounted activity meters for detecting cows in estrus on a large pasture-grazed dairy farm[J].Journal of Dairy Science,2012,95(6):3045-3056.
[10] MIGUEL J L S D.Rescounter Ⅱ:Un nuevo podómetro para optimizar el manejo reproductivo de la granja[J].Mg Mundo Ganadero,2007,19:54-55.
[11] NADAL J P,PARGA N.Duality between learning machines:A bridge between supervised and unsupervised learning[J].Neural Computation,2014,6(3):491-508.
[12] SATHYA R,ABRAHAM A.Comparison of supervised and unsupervised learning algorithms for pattern classification[J].International Journal of Advanced Research in Artificial Intelligence,2013,2(2):34-38.
[13] CASTELLI I,TRENTIN E.Combination of supervised and unsupervised learning for training the activation functions of neural networks[J].Pattern Recognition Letters,2014,37(37):178-191.
[14] WIEBE N,KAPOOR A,SVORE K.Quantum algorithms for nearest-neighbor methods for supervised and unsupervised learning[J].Quantum Information & Computation,2014,15(3):318-358.
[15] 刘涵,贺霖,李军.深度学习进展及其在图像处理领域的应用[J].中兴通讯技术,2017,23(4):36-40. LIU H,HE L,LI J.Advances in deep learning and its applications in image processing[J].ZTE Technology Journal,2017,23(4):36-40.(in Chinese)
[16] JUAN I H,CARLOS M O,HÉCTOR Y,et al.ZigBee-based wireless sensor network localization forcattle monitoring in grazing fields[J].Computers and Electronicsin Agriculture,2010,74(2):258-264.
[17] VOULODIMOS A S,PATRIKAKIS C Z,SIDERIDIS A B,et al.A complete farm management system based on animal identification using RFID technology[J].Computers & Electronics in Agriculture,2010,70(2):380-388.
[18] KWONG K H,WU T T,GOH H G,et al.Practical considerations for wireless sensor networks in cattle monitoring applications[J].Computers & Electronics in Agriculture,2012,81(1):33-44.
[19] FENG J Y,FU Z T,WANG Z Q,et al.Development and evaluation on a RFID-based traceability system for cattle/beef quality safety in China[J].Food Control,2013,31(2):314-325.
[20] ALSAAOD M,NIEDERHAUSER J J,BEER G,et al.Development and validation of a novel pedometer algorithm to quantify extended characteristics of the locomotor behavior of dairy cows[J].Journal of Dairy Science,2015,98(9):6236-6242.
[21] 郑家三,鲁明福,徐闯,等.奶牛主要群发性生产疾病早期预警系统的设计与实现[J].黑龙江八一农垦大学学报,2016,28(6):34-38. ZHENG J S,LU M F,XU C,et al.Design and realization of early warning system for the main mass production disease of dairy cattle[J].Journal of Heilongjiang Bayi Agricultural University,2016,28(6):34-38.(in Chinese)
[22] 邓志赟,刘财兴,曹维,等.基于PAM-RF的奶牛活动异常情况监测[J].广东农业科学,2015,42(16):122-129. DENG Z H,LIU C X,CAO W,et al.Behavior monitoring of dairy cattle using partitioning around medoids and random forest model (PAM-RF)[J].Guangdong Agricultural Sciences,2015,42(16):122-129.(in Chinese)
[23] 尹令,洪添胜,刘汉兴,等.结构相似子序列快速聚类算法及其在奶牛发情检测中的应用[J].农业工程学报,2012,28(15):107-112. YIN L,HONG T S,LIU H X,et al.Subsequence clustering algorithm based on structural similarity and its application in cow estrus detection[J].Transactions of the Chinese Society of Agricultural Engineering,2012,28(15):107-112.(in Chinese)
[24] 侯云涛,吴泽全,蔡晓华,等.奶牛行为特征识別系统的研究与设计[J].时代农机,2017,44(5):93-95. HOU Y T,WU Z Q,CAI X H,et al.The research and design for the identification system of cow behavior[J].Times Agricultural Machinery,2017,44(5):93-95.(in Chinese)
[25] 张淋江,崔先雨.基于无线传感器网络的奶牛行为与养殖环境监测的研究[J].电子测试,2015,17:7-11. ZHANG L J,CUI X Y.Study on cow behavior and breeding environment monitoring based on wireless sensor network[J].Electronic Test,2015,17:7-11.(in Chinese)
[26] MARTISKAINEN P,JÄRVINEN M,SKÖN J P,et al.Cow behavior pattern recognition using a three-dimensional accelerometer and support vector machines[J].Applied Animal Behavior Science,2009,119(1-2):32-38.
[27] 张鸿彦,许奇功.模糊聚类算法的优化设计[J].河南大学学报(自然版),2013,43(4):451-454. ZHANG H Y,XU Q G.Optimization design of fuzzy clustering algorithm[J].Journal of Henan University (Natural Science),2013,43(4):451-454.(in Chinese)
[28] 李滔,王士同.适合大规模数据集的增量式模糊聚类算法[J].智能系统学报,2016,11(2):188-199. LI T,WANG S T.Incremental fuzzy (c+p)-means clustering for large data[J].CAAI Transactions on Intelligent Systems,2016,11(2):188-199.(in Chinese)