鼠类鸣声的人工神经网络研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本课题得到国家自然科学基金项目(项目批准号:10274047)资助。动物鸣声是动物的一种很重要的生物行为,动物的声信号包含着很重要的、丰富的生物含义,其中最为重要的一点就是动物的声行为具有种的特异性,利用动物鸣声来进行分类已是动物系统分类学研究的热点。
     利用动物鸣声来进行分类在国内仅出现在鸟类和昆虫,哺乳动物利用鸣声分类基本未见。传统的鸣声分类时一般依据不同种动物鸣声信号在时域波形上的波形结构和脉冲率等的不同,功率谱上相对幅度最大所对应的频率即主频的不同来进行分类。传统鼠类的分类首先从外观上区分,如区分不开就需要进行解剖,根据其头盖骨来分类,这样的分类非常复杂而且需要专业人员。人工神经网络网络作为一门新兴的学科,从产生至今已经取得了长足的发展,被广泛深入地应用于模式识别、优化问题、图形图像处理、信号处理、自动控制、预测等等众多的领域,为这些领域相关问题的解决提供了新的有效的手段。本文我们采用人工神经网络的方法根据鸣声对不同种属的鼠类鸣声进行分析研究,有助于鼠类的分类简单化、自动化,且该分类方法分类速度快、准确率高。在国外,人工神经网络被广泛的应用到依据动物鸣声对同种动物不同个体的和同类不同种群的动物的分类的研究;而在国内,这个领域的研究基本处于空白。
     我们首先对多种动物的鸣声研究现状作了较为详细的总结分析,探讨了动物声通讯的生物学意义。鸣声作为依据在动物分类中、在害虫、鼠害的监测和防治工作中广泛应用以及应用动物的鸣声进行。
     针对鼠类叫声的分析提出了专业的录音话筒+专业声卡+计算机的数字录音方法。通过该方法尽可能的减少信号采集和存储中的中间环节,从而减少了噪声的引入和信号的畸变,避免了人的手工操作,同时也充分发挥了计算机自动程序执行、自动控制的能力,实现全自动不间断录音、存储。存储鸣声信号以WAV文件格式存在计算机的硬盘上,这样信号不易受到电、磁的干扰,使信号安全、准确和可靠。
     对录制好的信号,我们利用数字信号处理及神经网络等方面的理论知识,在Matlab的环境下自己编写了程序实现了对信号时域波形和频域功率谱的方
    
    便的手工分析,以认识信号的特征;在对信号的各种特征有了较深入的认识之
    后,用程序实现了信号自动分段分析、叫声信号自动截取以及叫声信号特征自
    动选择、提取;然后我们对所研究的大白鼠、甘肃盼鼠、黄胸鼠、小白鼠、棕
    色田鼠的各种状态下的叫声信号分别分成了验证样本集和训练样本集,每个样
    本集中都含有45个叫声信号文件;利用训练样本集对设计的人工神经网络(BP
    网络方案二)进行训练,训练成功的网络对训练样本集的样本识别率为100%,
    对验证样本集中样本的正确识别率可达到90%以上(大白鼠、甘肃黔鼠、黄胸
    鼠、小白鼠、棕色田鼠正确识别率分别为93.33%、97.78%、97.78%、95.56%、
    93.33%),并对实验结果作了进一步分析。实验结果表明,本文采用的人工神经
    网络的分类分析方法是更容易实现的、可行的和有效的,它较其他方法的突出
    的优点是极强的对叫声信号特征的自动提取能力和推广能力,是一种很有前途
    的分析方法。
This thesis is supported by National Science Fund (No. 10244047). Call is a main behavior of animals. Calls of animals contain important and abundant biological meanings, among which animal characteristics revealing is the most important. Calls based animal classification has become the hotspot of animal taxonomy.
    Calls based classification is used in avian and insects only recently and still not in mammals in China. Common methods classify animals by their difference in sound pulse rate, wave form structure in time domain and main peak frequency in frequency domain et cetera. Common methods classify mice first by appearance, then by dissection, which need manual operation of professionals and are sophisticated. As an emerging subject, artificial neural network (ANN) has been seen vast development ever since start, and been widely used in the fields of pattern recognition, optimization, image process, signal process, prediction etc, and provided novel and effective method for resolving relevant problem in these fields. Artificial neural network has been widly used in call based classification of individual from the same group and different group from the same species. Little has been done in this field in our country. In this paper ANN is used for classification of mice of different species by the analysis of mice cal
    ls. It makes mice classification simple, automatic, exact and fast.
    In this paper, Summarization of the status of call research and biological meaning of sound communication comes first, with disscussion of classification based on call-pattern recognition and inspection, prevention and cure of pests, mice using their calls. Followed by the introduction of ANN, its basic theory, basic algorithm, merit and defect of back propagation network and ANN application in pattern recognition field. Call based mice classification comes last.
    Compared with traditional sound recording, we put forward a method for gathering call signals using professional microphone, professional sound card and a
    
    
    
    computer. It reduces the processes needed in singal gathering as far as possible and without manual operation. It also makes full use of the automatic program execution ability of computer. So it can automatically record call signals and save gathered data in waveform format to hardisk without stop.
    Recorded data are processed by program developed in Matlab6.5 using theories of digital signal process, neural network, et cetera. It includes manual analyzation of signal, automatic sound finding and cutting out, automatic feature extraction, neural network training and validation. Experiments are carried on the recorded data of call of five species of mice. For both each species and for both training and validation 45 calls are used. The trained network obtains 100% recognition and more than 90% validation success. The result shows that ANN as a recognition method in calls of mice is very promising, effective and viable.
引文
[1] 俞清,刘如笋,鸟声研究介绍----国内外综述,动物学杂志,1995,30(1),52-55
    [2] 姜仕仁,丁平,李建华,红腹锦鸡鸣声声谱分析,动物学研究,1996,17(4),403-409.
    [3] 姜仕仁,丁平,邬艳春等,竹鸡鸣声特征分析,浙江大学学报(自然科学版),1996,23(2),188-193.
    [4] 姜仕仁,丁平,诸葛阳,大山雀领域鸣唱的声谱分析与比较研究,浙江大学学报(自然科学版),1998,25(1),69-73.
    [5] 丁平,诸葛阳,浙江西部白颈长尾雉栖息地片断化研究,动物学研究2000,21(1),65-69.
    [6] 姜仕仁,杭州鹊鸲的声行为,四川动物,2003,22(3),144-146.
    [7] 姜仕仁,丁平,王亦生等,山鹡领繁殖期的领域鸣唱特征分析,生态学杂志1999,18(4),40-41.
    [8] 姜仕仁,丁平,诸葛阳,等,白头鹎繁殖期鸣声行为的研究,动物学报1996,42(3),253~259.
    [9] 姜仕仁,丁平,诸葛阳,嵊泗岛和杭州地区白头鹎鸣声特征比较研究,动物学研究,1994,15(3),19~27.
    [10] 姜仕仁,丁平,施青松等,动物鸣叫声计算机分析,生态学杂志,1995,14(5),1-7.
    [11] 姜仕仁,丁平,施青松,等,白头鹎方言的初步研究,动物学报,1996,42(4),361~367.
    [12] 姜仕仁,丁平,诸葛阳,三种蛙鸣声特征比较研究,动物学研究,1995,16(1),75-81.
    [13] 吉敬合,韩春琏,马志远,一种画眉雌性鸣声波形和频谱特征,山西大学学报(自然科学版),1995,18(3),280-284.
    [14] 加米拉,乌旭,汪大伟等,朱雀鸣声声谱与语图的初步分析,东北师大学报(自然科学版),2000,32(1),71-73.
    [15] 刘如笋,丁文宁,赵欣如,丽色噪鹛鸣声的语图结构初步研究,动物学报,1997,43(增刊),69-72.
    
    
    [16] 俞清,刘如笋,强脚树莺雄鸟的两种歌声,动物学杂志,1999,34(4),17-19.
    [17] 刘如笋,俞清,丁文宁等,橙翅噪鹛的声行为,动物学报,1997,43(增刊),73-78.
    [18] 刘如笋,俞清,赵欣如,三趾鸦雀的鸣叫型,动物学杂志,1998,34(4),18-21.
    [19] 雷富民,鸟类鸣声结构地理变异及其分类学意义,动物分类学报,1999,24(2),232-240.
    [20] 雷富民,鸟类鸣声在鸟类系统学研究中的作用初探,动物分类学报,1999,24(4),461-466.
    [21] 李恺,郑哲民,棺头蟋属六种常见蟋蟀鸣声特征分析与种类鉴定(直翅目,蟋蟀总科),昆虫分类学报,1999,21(1),17-21.
    [22] 李恺,廉振民,湖北省三种蟋蟀鸣声结构分析(直翅目,蟋蟀总科),昆虫分类学报,1999,21(3),187-190.
    [23] 吴福桢,冯平章,何忠,北京及银川常见蟋蟀鸣叫习性与种类鉴定,昆虫学报,1986,29(1),62-66.
    [24] 杨培林,常岩林,芦荣胜,日本条螽鸣声特征的初步研究,广西科学院学报,2000,16(3),138-141.
    [25] 石福明,杨培林,蒋书楠,鼻优草螽和苍白优草螽鸣声和发声器的研究,动物学研究,2001,22(2),89-92.
    [26] 石福明.杨培林.杜喜翠,日本条螽不同地理种群雄性鸣声的比较研究(直翅目,露螽科),动物分类学报,2003,28(3),402-410.
    [27] 沈钧贤等,短翅鸣螽的鸣声特征分析与听觉研究,声学学报,1991,16(6),459~465.
    [28] Fleming, C.A.,Acoustic behaviour as a generic character in New Zealand cicadas ,J.R.Soc.N.Z., 1975,5(1),47-64.
    [29] Ewart,A.,Revisionary notes on the genus Pauropsatta Goding and Froggatt With special reference to Queensland, Mem.Qd Mus,1989,27(2),289-375.
    [30] Fleming,C.A.,The cicada genus Kikihia Dugdale part 1,The New Zealand green foliage cicada Natn.,Mus.N.Z.R.,1984,18(2),191-206.
    [31] 蒋锦昌,杨新宇,陈浩,黑蚱蝉的叫声模式和神经肌肉活动特征,声学学报,2000,25(5),429-434.
    [32] 雷仲仁,蒋锦昌,李莉等,不同地区蟪蛄蝉求偶鸣声的比较,昆虫学报,1997,40(4),349-357.
    [33] 蒋锦昌,杨新宇,刘向群,蟪蛄蝉的两种行为叫声及其发声机制的分析,
    
    声学学报,1996,21(4),313-318.
    [34] 蒋锦昌,杨新宇,唐欢,蝉类用于声通讯的鸣声特性及其飞行趋声范围的估计,声学学报(中文版),1995,20(3),226-231.
    [35] 雷仲仁,周尧,李莉,蝉鸣特征及其在分类学上的意义,昆虫分类学报,1994,16(1),51-58.
    [36] 雷仲仁,李莉,闵一健等,不同地区黑蚱蝉的形态结构与鸣声比较研究,西北农业学报,1994,3(2),48-52.
    [37] 何忠,陈念丽,北京地区五种常见鸣虫的鸣声结构,动物学报,1985,31(4),324-330.
    [38] 曹立民,郑哲民,廉振民,东北地区跃度蝗属鸣声结构的比较研究(直翅目,网翅蝗科),昆虫分类学报,1995,17(1),70-74.
    [39] 郑哲民,中国蝗虫的分类学研究,2003,31(专辑),46-58.
    [40] 何忠,蝼蛄的声学通讯,生物学通报,1995,30(12),6-7.
    [41] 何忠,陈念丽,席瑞华,非洲蝼蛄的鸣声结构及声引诱,动物学报,1989,35(1),73-81.
    [42] 张志涛,昆虫声通讯浅述与稻飞虱鸣声研究,生命科学,1997,9(5),227-230
    [43] Snowdon C.T.,Cleveland J.,French J.A., Response to context-and individualspecific cues in cotton-top tamarin long calls,Anim.Behav.,1983,31,92-101.
    [44] Tooze Z.J.,Harrington F.H.,Fentress J.C.,Individually distinct vocalizations in timber wolves(Canis INpus), Anim.Behav.1990,40,723-730.
    [45] Mitani J.C.,Gros-louis,J.,Macedonia,J.m.,Selection for acoustic individuality within the vocal repertoire of wild chimpanzees, Int.J.Primatol,1996, 17, 569-583.
    [46] Frommolt K.H.,Kruchenkova E.P,Russing H.,Individuality of territorial barking in arctic foxes,Z.Saugetierk Suppl.,1997,2,66-70.
    [47] Zingg, P. E.,Acoustics species identification of bats(Mamma21ia: Chiroptera) in Swizerland, Rev. Suisse Zool.,1990,97,263-294.
    [48] Au ,W. W. L. ,L. N. Andersen , A. R. Rasmussen et al,Neural network modeling of a dolphin' s sonar discrimination capapilities, Journal of Acoustic Society of America ,1995,98,43-50.
    [49] Molliver, M. E., Operant control of vocal behavior in the cat, Journal of the Experimental Analysis of Behavior, 1963,6, 197-202.
    
    
    [50] Janik, V. M. & Slater, P. J. B., Vocal learning in mammals,Advances in the Study of Behavior, 1997,26, 59-99.
    [51] Weary, Daniel M., Fraser. David, Vocal response of piglets to weaning: effect of piglet age, Applied Animal Behaviour Science, 1997, 54 (2), 153-160
    [52] Weary Daniel M.,Ross Stephen, Fraser David, Vocalizations by isolated piglets:a reliable indicator of piglet need directed towards the sow, Applied Animal Behaviour Science, 1997,53(4),249-257.
    [53] Pajor E.A.,Weqry D.M.,Alternative hpusing for sows and litters:Effects of sow-controlled housing on responses to weaning, Applied Animal Behaviour Science, 1999,65(2),105-121.
    [54] Weary Daniel M.,Chua Beverly, Effects of early separation on the dairy cow and calf: 1. Separation at 6 h, 1 day and 4 days after birth, Applied Animal Behaviour Science, 2000,69(3),177-188.
    [55] Marchant-Forde Jeremy N.,Marchant-Forde Ruth M.,Responses of dairy cows and calves to each other's vocalisations after early separation, Applied Animal Behaviour Science, 2002,78(1),19-28.
    [56] Watts Joe M.,Stookey joseph M., Vocal behaviour in cattle: the animal's commentary on its biological processes and welfare,2000,67(1),15-33.
    [57] Reby David,Cargnelutti Bruno,Spectral acoustic structure of barking in roe deer (Capreolus capreolus). Sex-, age- and individual-related variations, C.R.Acod.Sci. Paris.Sciences de la vie/Life Sciences,1999,322,271-279.
    [58] 韩春琏,陕方,曹家林,大熊猫的吠叫声特征与家狗的吠声比较,声学学报,2001,26(3),264-271.
    [59] 韩春琏,陕方,曹家林,大熊猫“唔”叫声的时域和频域特征,声学学报,2000,25(4),264-270.
    [60] 张树义,王立新,人工神经网络在蝙蝠回声定位叫声识别方面的应用,动物学杂志,2001,36(4),74-77.
    [61] 张树义,赵辉华,冯江等,蝙蝠回声定位与捕食对策的研究,动物学杂志,1999,34(6),47-50.
    [62] 程明华,黄凤鹏,于新胜,威德尔海豹发声的信号特征初步研究,极地研究,1998,10(4),272-281.
    [63] 王丁,王克雄,赤松友成等,白鱀豚哨叫声的研究,海洋与湖沼,1999,30(4),349-354.
    
    
    [64] 王丁,长江江豚声信号及其声行为的初步研究,水生生物学报,1996,20(2),127-133.
    [65] 荆显英,肖友芙,景荣才,白鱀豚的声信号及声行为,中国科学,1981,2,233-239.
    [66] Balph D. M. ,Balph D. E, Sound communication of Uinta ground squirrels, J. Mamm., 1966,47 (3),440-450.
    [67] Dunford C. ,Davis R. , Cliff chipmunk vocalizations and relevance to the taxonomy of coastal Snonoran chipmunks, J. Mamm., 1975,56, 207- 212.
    [68] Emmons L.H., Sound communication among African rain forest squirrels, Z. Tierpsych., 1978,47,1- 49.
    [69] Melchior H.R., Characteristics of arctic ground squirrel alarm calls , Oecologia, 1971, 7,184 - 190.
    [70] Owings D.H.,Ross A.V., Alarm calls of Californian ground squirrels Spermophilus beecheyi, Z. Tierpsych., 1978,46,260- 267.
    [71] Waring G.H, Sound communication of black2tailed ,white2tailed andgunnison prairie dogs, Am. Midl.Nat.,1970,83,167- 185.
    [72] Watts C.H.S., Vocalizations of nine species of rat (Rattus:Muridae), J. Zool., 1980, 191, 531- 555.
    [73] Smith C.C., Structure and function of the vocalizations of tree squirrels (Tamiasciurus), J. Mammal, 1978,59,793- 808.
    [74] Rado R.,Levi N.,Hauser H.et al,Seismic signalling as a means of communication in a subterranean mammal ,Anim. Behav., 1987,35,1249-1266.
    [75] Nevo E.,Heth G.,Beiles A.et al, Geographic dialects in blind mole rats: Role of vocal communication in active speciation , Proc. Natl . Acad . Sci . USA, 1987, 84,3312- 3315.
    [76] Stefan M.B.,Eva M.C.Chiu, Behavioural responses of laboratory rats to playback of 22khz ultrasonic calls,Phy, & Bahav.,1995,57(6),1039-1044.
    [77] Blumberg M.S.,Alberts J.R.,On the significance of similiarities between ultrasonic vocalization of infant and adult rats, Neuro. and Biobehav. Rev. 1991,15,383-390.
    [78] 蒋锦昌,徐慕玲,王强,褐家鼠声行为的种特性和种族变异,遗传学报,1993,20(1),33-43.
    [79] 邰发道,王廷正,闵一建,棕色田鼠的发声及其频谱分析,动物学研究,
    
    1999,20(4),278-283.
    [80] 李金钢,何建平,王廷正等,甘肃鼢鼠鸣声声谱分析,动物学研究,2000,21(6),458-462.
    [81] 李金钢,王廷正,何建平等,甘肃鼢鼠的震动通讯,兽类学报,2001,21(2),153-154.
    [82] 何其超,房斌,龙建忠等,草原鼠兔鸣叫声的观察和声学特征分析,声学学报,1996,21(4),679-684.
    [83] W.S.McCulloch., W.Pitts., A Logical calculus of the ideas immanent in Nervous Activity. Bill Math. Biophysics, 1943, 5, 115-133.
    [84] Hebb.D.O., The organization of Behavior, Wiley, 1949.
    [85] Rosenblatt.F.,The perceptron:A preceiding and recognizing automation ,Cornell Aeronauticall Laboratory, 1957,85-460-1.
    [86] Rosenblatt.F., Principles of Neurodynamicas, Spartam, 1961.
    [87] B.Widrow, Generalization and information storage in networks of adaline "neurons". In Self Organizing Systems 1962. M Yovitz. G. Jacobi and G. Goldstein. Eds. Washington. DC: Spartan Books. 1962: 435-461.
    [88] Minsky M., and S. Papert, Perceptrons, MIT Press, 1969.
    [89] J.J.Hopefield, Neural Networks and physical systems with emergent collective computational abilities, Proc.Natl.Acas.Sci., vol.79, Apr,1982: 2554-2558.
    [90] Rumelhart D., McCelelland J. Parallel Distributed Processing, Explorations in the Microstructure of Cognition. Cambridge: Bradford Books, MIT Press. 1986.
    [91] 黄德双,神经网络模式识别系统理论,电子工业出版社,1996年5月.
    [92] 边肇祺等,模式识别,清华大学出版社,2000年1月第2版.
    [93] 张立明,人工神经网络的模型及其应用,第1版,上海:复旦大学出版社,1993年.
    [94] 王伟,人工神经网络原理——入门与应用,北京航空航天大学出版社,1995.
    [95] 袁曾任,人工神经网络及其应用,清华大学出版社,1999.
    [96] 郭敏,尚志远,基于Matlab软件实现储粮害虫声信号的时频分析,陕西师范大学学报(自然科学版),2002,30(3),62-66.
    [97] 楼顺天,施阳,基于MATLAB的系统分析与设计,西安电子科技大学出版社,1999.
    [98] 张建敏等译,Windows环境下的多媒体程序设计,学苑出版社,1994

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700