臺灣博碩士論文加值系統

近年來隨著人口的成長及經濟發展，自然生態環境已受到極大破壞。在都市已經很難得聽見青蛙的鳴聲，除了讚嘆蛙鳴的美妙，我們希望能更進一步的了解牠們，環顧四周，不見青蛙的蹤跡，又無法光憑青蛙叫聲來認識這麼多種類的青蛙，因此希望發展出一套簡易又快速的程式，能自動判別青蛙的種類。
在本篇研究中我們使用現有人類語音處理技術中的能量法與梅爾倒頻譜分析法，及類神經網路理論來分類，使用的策略是取音量值超過背景音量的門檻值則視為蛙鳴的一音節，取其12維mfcc的平均值、12維mfcc的變異數、12維mfcc中最大最小值發生的音框，共48維，辨識結果有70%的正確率。
近年來兩棲動物數量急劇下降，其所面臨的生態危機，已給人類帶來不可忽視之警訊；近來為推動以生態工法達成水質淨化，有效改善與維持水庫水體，防止水庫優養化現象，陸續於翡翠水庫集水區建立生態工法淨化設施，坪林渡南橋溼地為其中之一，且其環境為北勢溪與坡地之交界地帶，是該處附近最適合青蛙繁殖活動的地點之一。
陸水共生之生物大部分生態系統行為多在水岸邊發生，而台灣目前尚缺乏相關設計規範可供參考，本研究於坪林渡南橋人工溼地共設立40點，先測試噪音計調查之可行性，之後分別調查各點重要的棲地因子及青蛙的數量與出現種數，使用多變量分析探討各變項之間的相關性。
結果顯示噪音計調查可用於小雨蛙，且青蛙數量與坡度成負相關，坡度設計建議值<40度，且池塘大小、植物多樣性、植物密度與出現蛙種數呈正相關，池塘面積建議大於500平方公尺，大安水簑衣密度建議為0.4-0.6株數/公分，可作為人工溼地青蛙廊道設計之參考。

In recent years, along with the population growth and the economical development, the natural ecological environment received enormous suffering, threatening the survival of frogs. In metropolis'' hustle, people can hardly hear the simple frogs’ song anymore. While acclaiming its pure wonderfulness, we wish to understand them better. However, as we look around without any trace of frogs, and the frog''s sound difference too much for the human ears to tell one kind from another, we hopes to develops a set of simple, quick computer formulas that can automatically recognize which types of frog by the sound it made.
This study was combined with energy method, MFCC feature method, and neural networks to recognize the species of frogs. If the volume was over the set threshold, it was defined as one syllable. We extracted the first twelve MFCC features from every syllable, then analyzed its mean, variation, and the position which the max and min values appeared. Eventually, forty-eight dimensions was input to train and test. The result shows the accuracy was up to 70%.
Declines in amphibian populations have been noted all over the world and perceived as one of the most critical threats to global biodiversity. Wetland managers need more information concerning amphibian habitat requirements. There is a new artificial wetland between the Bai-Shi River and local community. It is the best buffer zone for amphibian production activity there。
Most ecosystems of amphibian animals took place on the lake banks, yet there was less related design solutions offered in Taiwan. This research selected 40 sample sites in Du-Nan Wetland. We test the feasibility for measuring frog abundance by sound-level meter first, and then study the relationship between some important habitat variables and frogs by factor analysis.
The result shows that sound-level meter can be used for measuring the abundance of Microhyla ornata Dumeril. Also, the amounts of frog and the bank slope are negatively relative. Bank slope is designed to be less than 40 recommending degrees. The pond size, plant diversity and plant density are positively relative to the species richness. The pond size is recommended to be larger than 500 square meters. The density of Hydrophila pogonocalyx Hayata is recommended to be 0.4-0.6 per stem/cm. Thos can be reference for designing frog corridor.

目錄
中文摘要………………………………………………………………… Ⅰ
英文摘要………………………………………………………………… Ⅱ
目錄……………………………………………………………………… Ⅲ
圖目錄…………………………………………………………………… IV
表目錄…………………………………………………………………… IV
第一章、前言…………………………………………………………… 1
第二章、前人研究……………………………………………………… 2
第三章、理論概述……………………………………………………… 3
3.1 SOM類神經網路………………………………………………… 3
3.2 梅爾刻度式倒頻譜特徵值求取………………………………… 3
3.3 訓練網路資料選取方法………………………………………… 8
3.4 聲音採集………………………………………………………… 8
第四章、結果與討論…………………………………………………… 9
第五章、結論與建議…………………………………………………… 13
第六章、參考文獻……………………………………………………… 14
IV
圖目錄
圖3-1 SOM網路概念圖………………………………………………… 3
圖3-2 梅爾刻度式倒頻譜特徵參數擷取流程………………………… 5
圖4-1 平均值值權重………………………………………………………… 9
圖4-2 變異數值權重………………………………………………………… 9
圖4-3 最大值音框權重……………………………………………………… 10
圖4-4 最小值音框權重……………………………………………………… 10
表目錄
表一 實測值與網路辨識之結果值…………………………………………… 11

中文摘要………………………………………………………………… Ⅰ
英文摘要………………………………………………………………… Ⅱ
目錄……………………………………………………………………… Ⅲ
圖目錄…………………………………………………………………… IV
表目錄…………………………………………………………………… IV
第一章、前言…………………………………………………………… 1
第二章、材料與方法…………………………………………………… 4
2.1 研究地點……………………………………………………… 4
2.2 蛙類調查……………………………………………………… 6
2.3 環境變數……………………………………………………… 6
2.4 統計分析……………………………………………………… 7
2.4.1 原始數據標準化 8
2.4.2 對相關矩陣作主成分分析 9
2.4.3 確定主因子 10
2.4.4 因子軸的旋轉 12
2.4.5 因子得分的計算 13
第三章、結果與討論…………………………………………………… 15
3.1 噪音計調查之可行性………………………………………… 15
3.2 因子分析……………………………………………………… 15
3.2.1 主成份一……………………………………………… 16
3.2.2 主成份二……………………………………………… 18
3.2.3 主成份三-五…………………………………………… 18
3.3 棲地選擇……………………………………………………… 19
第四章、結論與建議…………………………………………………… 20
第五章、參考文獻……………………………………………………… 21
圖目錄
圖2-1 研究地區樣本點位置圖………………………………………… 5
圖2-2 因子軸旋轉示意圖……………………………………………… 13
圖3-1 小雨蛙數量與測得音量關係圖………………………………… 17
圖3-4 植物總密度與小雨蛙數量關係圖……………………………… 17
圖3-5 池塘面積與出現蛙種數關係圖………………………………… 17
圖3-6 植物多樣性與出現蛙種數關係圖……………………………… 17
圖3-7 水面上坡度與小雨蛙出現隻數關係圖………………………… 18
圖3-8 主成份一、二因子得分圖……………………………………… 19
表目錄
表3-1 坪林溼地青蛙與棲地因子因子分析之主成份負荷…………… 16

1.王毅男, 梁冰, and 張樹義. 2005. 四種企鵝叫聲特徵的比較. 動物學研究 26:590-594.
2. 許嘉晉. 2001. 聲音訊號的分類.
3.Anderson, S. E., A. S. Dave, and D. Margoliash. 1996. Template-based automatic recognition of birdsong syllables from continuous recordings. J. Acoust. Soc. Am 100:1209–1219.
4.Campbell, R. H., S. K. Martin, I. Schneider, and W. R. Michalson. 1996. Analysis of mosquito wing beat sound. The Journal of the Acoustical Society of America 100:2710.
5.Chesmore, E. D. 2001. Application of time domain signal coding and artificial neural networks to passive acoustical identification of animals. Applied Acoustics 62:1359-1374.
6.Chesmore, E. D., and C. Nellenbach. 1997. Acoustic methods for the automated detection and identification of insects. III International Symposium on Sensors in Horticulture 562:223-231.
7.Chesmore, E. D., M. D. Swarbrick, and O. P. Femminella. 1997. Automated analysis of insect sounds using TESPAR and expert systems–a new method for species identification. Information Technology, Plant Pathology and Biodiversity. Wallingford, UK: CAB International:273-287.
8.Clemins, P. J., and M. T. Johnson. 2002. Automatic type classification and speaker verification ofAfrican Elephant vocalizations. Vrije Universiteit, Netherlands: International Conference on Animal Behavior, Proceedings.
9.Dunson, W. A., R. L. Wyman, and E. S. Corbett. 1992. A symposium on amphibian declines and habitat acidification. Journal of Herpetology 26:349-352.
10.McIlraith, A. L., and H. C. Card. 1995. Birdsong recognition with DSP and neural networks. WESCANEX 95. Communications, Power, and Computing. Conference Proceedings. IEEE 2.
11.Murray, S. O., E. Mercado, and H. L. Roitblat. 1998. The neural network classification of false killer whale (Pseudorca crassidens) vocalizations. The Journal of the Acoustical Society of America 104:3626.
12.Ohya, E., and E. D. Chesmore. 2003. Automated identification of grasshoppers by their songs. Annual Meeting of the Japanese Society of Applied Entomology and Zoology.
13.Parsons, S. 2001. Identification of New Zealand bats in flight from analysis of echolocation calls by artificial neural networks. Journal of Zoology (London) 253:447-456.
14.Parsons, S., and G. Jones. 2000. Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks. Journal of Experimental Biology 203:2641-2656.
15.Pechmann, J. H. K., and H. M. Wilbur. 1994. Putting declining amphibian populations in perspective: natural fluctuations and human impacts. Herpetologica 50:65-84.
16.Reby, D., S. Lek, I. Dimopoulos, J. Joachim, J. Lauga, and S. Aulagnier. 1997. Artificial neural networks as a classification method in the behavioural sciences. Behav. Processes 40:35-43.
17.Taylor, A., G. Grigg, G. Watson, and H. McCallum. 1996. Monitoring frog communities: an application of machine learning. Proceedings of the 8th Innovative Applications of Artificial Intelligence Conference:1564–1596.
18.Terry, A. M. R., and P. K. McGregor. 2002. Census and monitoring based on individually identifiable vocalizations: the role of neural networks. Animal Conservation 5:103-111.
19.Vaughan, N., G. Jones, and S. Harris. 1997. Identification of British bat species by multivariate analysis of echolocation call parameters. Bioacoustics 7:189-207.

1.行政院環境保護署動物生態評估技術規範. 2004. 環保署.
2.Babbitt, K. J., and G. W. Tanner. 2000. Use of temporary wetlands by anurans in a hydrologically modified landscape. Wetlands 20:313-322.
3.Beebee, T. J. C., and T. J. Beebee. 1996. Ecology and Conservation of Amphibians. Chapman & Hall. U.S.A.
4.Binckley, C. A., and W. J. Resetarits Jr. 2003. Functional equivalence of non-lethal effects: generalized fish avoidance determines distribution of gray treefrog, Hyla chrysoscelis, larvae. Oikos 102:623-629.
5.Bosch, J., and I. Martíez-Solano. 2003. Factors influencing occupancy of breeding ponds in a montane amphibian assemblage. Journal of Herpetology 37:410-413.
6.Dunson, W. A., R. L. Wyman, and E. S. Corbett. 1992. A symposium on amphibian declines and habitat acidification. Journal of Herpetology 26:349-352.
7.Fairweather, P. G., and G. M. Napier. 1998. Environmental Indicators for National State of the Environment Reporting: Inland Waters. Dept. of Environment, Australia.
8.Ficetola, G. F., and F. De Bernardi. 2004. Amphibians in a human-dominated landscape: the community structure is related to habitat features and isolation. Biological Conservation 119:219-230.
9.Freda, J., and W. A. Dunson. 1986. Effects of low pH and other chemical variables on the local distribution of amphibians. Copeia 1986:454-466.
10.Fujioka, M., and S. J. Lane. 1997. The impact of changing irrigation practices in rice fields on frog populations of the Kanto Plain, central Japan. Ecological Research 12:101-108.
11.Halverson, M. A., D. K. Skelly, J. M. Kiesecker, and L. K. Freidenburg. 2003. Forest mediated light regime linked to amphibian distribution and performance. Oecologia 134:360-364.
12.Healey, M., D. Thompson, and A. Robertson. 1997. Amphibian communities associated with billabong habitats on the Murrumbidgee floodplain, Australia. Australian Journal of Ecology 22:270-278.
13.Joly, P., and A. Morand. 1997. Amphibian diversity and land-water ecotones. Biodiversity in land-water ecotones. Man and biosphere series 18:161-182.
14.Lichtenberg, J. S., S. L. King, J. B. Grace, and S. C. Walls. 2006. Habitat associations of chorusing anurans in the lower Mississippi River alluvial valley. Wetlands 26:736-744.
15.Marsh, D. M., G. S. Milam, N. P. Gorham, and N. G. Beckman. 2005. Forest roads as partial barriers to terrestrial salamander movement. Conservation Biology 19:2004-2008.
16.Mousseau, T. A., and C. W. Fox. 1998. The adaptive significance of maternal effects. Trends in Ecology & Evolution 13:403.
17.Pavignano, I., C. Giacoma, and S. Castellano. 1990. A multivariate analysis of amphibian habitat determinants in north western Italy. Amphibia-Reptilia 11:311-324.
18.Pechmann, J. H. K., and H. M. Wilbur. 1994. Putting declining amphibian populations in perspective: natural fluctuations and human impacts. Herpetologica 50:65-84.
19.Petranka, J. W., M. E. Hopey, B. T. Jennings, S. D. Baird, and S. J. Boone. 1994. Breeding habitat segregation of wood frogs and American toads: the role of interspecific tadpole predation and adult choice. Copeia 1994:691-697.
20.Pierce, B. A. 1985. Acid tolerance in amphibians. Bioscience 35:239-243.
21.Porej, D., M. Micacchion, and T. E. Hetherington. 2004. Core terrestrial habitat for conservation of local populations of salamanders and wood frogs in agricultural landscapes. Biological Conservation 120:399-409.
22.Resetarits, W. J. 2005. Habitat selection behaviour links local and regional scales in aquatic systems. Ecology Letters 8:480-486.
23.Rudolf, V. H. W., and M. O. Rödel. 2005. Oviposition site selection in a complex and variable environment: the role of habitat quality and conspecific cues. Oecologia 142:316-325.
24.Semlitsch, R. D., and J. R. Bodie. 2003. Biological Criteria for Buffer Zones around Wetlands and Riparian Habitats for Amphibians and Reptiles. Conservation Biology 17:1219-1228.
25.Shannon, C. and W. Weaver. 1949. The mathematical theory of communication. Illinois: University of Illinois Press.
26.Skelly, D. K., E. E. Werner, and S. A. Cortwright. 1999. Long-term distributional dynamics of a Michigan amphibian assemblage. Ecology 80:2326-2337.
27.Snodgrass, J. W., M. J. Komoroski, A. L. Bryan, and J. Burger. 2000. Relationships among isolated wetland size, hydroperiod, and amphibian species richness: implications for wetland regulations. Conservation Biology 14:414-419.
28.Stebbins, R. C., and N. W. Cohen. 1995. A Natural History of Amphibians. Princeton University Press. U.S.A.
29.Van De Mortel, T., and R. Goldingay. 1998. Population assessment of the endangered Green and Golden Bell Frog Litoria aurea at Port Kembla, New South Wales. Australian zoologist 30:398-404.
30.Viertel, B. 1999. Salt tolerance of Rana temporaria: spawning site selection and survival during embryonic development (Amphibia, Anura). Amphibia-Reptilia 20:161-171.
31.Wassersug, R. J., and D. G. Sperry. 1977. The relationships of locomotion to differential predation on Pseudacris Triseriata (Anura: Hylidae). Ecology 58:830-839.
32.Welsh Jr, H. H., and L. M. Ollivier. 1998. Stream amphibians as indicators of ecosystem stress: a case study from California''s redwoods. Ecological Applications 8:1118-1132.