摘要
[目的]针对目前平养肉鸡跛行检测主要依靠饲养员的人为观察,存在主观因素强、效率低等问题,提出一种基于三轴加速度传感器的肉鸡步态检测方法。[方法]研制了一种基于三轴加速度传感器的无线运动脚环,通过肉鸡行走自检测(WSD)算法确定肉鸡行走的有效数据点,利用逻辑回归算法建立肉鸡健康与跛行二分类模型,最后通过欧氏距离度量肉鸡跛行程度。[结果]无线运动脚环能快速采集和传输肉鸡腿部运动信息,肉鸡健康与跛行二分类模型的平均准确率为93.88%,通过欧氏距离可以近似表征肉鸡跛行的严重程度。[结论]提出了一套肉鸡步态自动检测算法,为平养条件下肉鸡步态检测提供一种新方法。
[Objectives]The current modes of broiler lameness detection system mainly rely on breeders,and hence are always faced with the problem of subjectivity and unreliability. This study proposes a gait detection system based on three-axis acceleration sensor.[Methods]A wireless foot-loop based on three-axis acceleration sensor was developed. The effective data points for broiler walk was determined by a walking self-detection( WSD) algorithm. Logistic Regression algorithm was used to establish a two-class model for health-lameness in broilers,and finally,the degree of lameness was measured by Euclidean distance. [Results]The test results showed that the wireless foot-loop could quickly collect and transmit the broiler leg movement information. The average accuracy rate of broiler health-lameness two-class model was 93.88%. The Euclidean distance approximated the extent of lameness. [Conclusions]An automatic detection algorithm for broiler gait was proposed to provide a new method for broiler gait detection underfloor system.
引文
[1]张瑞娟.中国肉鸡产业发展现状及趋势[J].江苏农业科学,2016,44(1):448-451.Zhang R J. The status and trend of China broiler industry development[J]. Jiangsu Agricultural Sciences,2016,44(1):448-451(in Chinese).
[2] Caulfield M P,Cambridge H,Foster S F,et al. Heat stress:a major contributor to poor animal welfare associated with long-haul live export voyages[J]. The Veterinary Journal,2014,199(2):223.
[3] David B,Moe R D,Michel V,et al. Air quality in alternative housing systems may have an impact on laying hen welfare. PartⅠ:dust[J].Animals,2015,5(3):495-511.
[4]李鹏飞,姜敏,史超颖,等.规模化养殖场肉鸡腿病情况调查[J].畜牧与兽医,2016,48(6):116-118.Li P F,Jiang M,Shi C Y,et al. An investigation of broiler leg disorders in large-scale farms[J]. Animal Husbandry&Veterinary Medicine,2016,48(6):116-118(in Chinese).
[5] Mc Namee P T,Mc Cullagh J J,Thorp B H,et al. Study of leg weakness in two commercial broiler flocks[J]. Veterinary Record,1998,143(5):131-135.
[6]沈良诚,Morris M P.美国对肉鸡腿疾的全国性调查情况[J].国外畜牧学:猪与禽,1993,13(6):42-45.Shen L C,Morris M P. National survey of broiler leg diseases in the United States[J]. Animal Science Abroad:Pigs&Poultry,1993,13(6):42-45(in Chinese).
[7]史红梅.肉鸡腿病发生的原因及防制措施[J].农业技术与装备,2017(6):93-94.Shi H M.Causes and control measures of chicken leg disease[J]. Agricultural Technology&Equipment,2017(6):93-94(in Chinese).
[8]沈明霞,刘龙申,闫丽,等.畜禽养殖个体信息监测技术研究进展[J].农业机械学报,2014,45(10):245-251.Shen M X,Liu L S,Yan L,et al. Review of monitoring technology for animal individual in animal husbandry[J]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(10):245-251(in Chinese with English abstract).
[9] Thorup V M,Munksgaard L,Robert P E,et al. Lameness detection via leg-mounted accelerometers on dairy cows on four commercial farms[J].Animal,2015,9(10):1704-1712.
[10] Alsaaod M,Romer C,Kleinmanns J,et al. Electronic detection of lameness in dairy cows through measuring pedometric activity and lying behavior[J].Applied Animal Behaviour Science,2012,142(3/4):134-141.
[11]姜永彬.福利饲养技术对肉仔鸡生产性能和福利状态的影响[D].泰安:山东农业大学,2010.Jiang Y B. Effects of welfare rearing techniques on the performance and welfare of broilers[D]. Tai’an:Shandong Agricultural University,2010(in Chinese with English abstract).
[12]刘龙申,沈明霞,姚文,等.基于加速度传感器的母猪产前行为特征采集与分析[J].农业机械学报,2013,44(3):192-196.Liu L S,Shen M X,Yao W,et al. Acquisition and analysis of sows’behavior before farrowing based on acceleration sensor[J]. Transactions of the Chinese Society for Agricultural Machinery,2013,44(3):192-196(in Chinese with English abstract).
[13]张俊杰,孙光民,李煜,等.基于加速度传感器的上肢运动信息采集与姿态识别[J].北京工业大学学报,2017,43(7):978-986.Zhang J J,Sun G M,Li Y,et al. Upper limb motion information acquisition and gesture recognition based on acceleration sensor[J]. Journal of Beijing University of Technology,2017,43(7):978-986(in Chinese with English abstract).
[14]赵阳,娄小平,刘锋,等.自适应MEMS加速度计滤波算法[J].传感器与微系统,2016,35(11):120-122.Zhao Y,Lou X P,Liu F,et al. Adaptive filtering algorithm of MEMS accelerometer[J]. Transducer and Microsystem Technologies,2016,35(11):120-122(in Chinese with English abstract).
[15] Kestin S,Knowles T,Tinch A,et al. Prevalence of leg weakness in broiler chickens and its relationship with genotype[J]. Veterinary Record,1992,131(9):190-194.
[16]邢秀玉,刘鸿宇,黄武.基于加速度传感器的步态分类研究[J].传感器世界,2013,19(4):10-13.Xing X Y,Liu H Y,Huang W. Research on gait classification based on accelerometers[J]. Sensor World,2013,19(4):10-13(in Chinese with English abstract).
[17] Menard S. Applied logistic regression analysis[J]. Technometrics,1996,38(2):192.